Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions related to emotions and interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Japanese verbs or verb stems

    np_acts-logits-general · gemini-2.0-flash

    verb conjugations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fermés
    -0.63
    Opening
    -0.55
     closing
    -0.54
     fermée
    -0.53
     Opening
    -0.53
     mijne
    -0.53
     ouverts
    -0.51
     fermeture
    -0.50
     opening
    -0.49
     tickets
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    1.05
    SequentialGroup
    0.89
    Autoritní
    0.87
     Мексичка
    0.84
    aarrggbb
    0.80
    saraba
    0.80
    \{\\
    0.79
     '\\;'
    0.78
     autorytatywna
    0.78
     MainAxisSize
    0.76
    Act Density 0.259%

    No Known Activations