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

    Neuronpedia

    INDEX
    Explanations

    references to variables and constants in programming or code contexts

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

    code parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.57
     kaarangay
    -0.53
     Infórmanos
    -0.52
     citoy
    -0.45
     magique
    -0.44
     nødven
    -0.44
     réaliste
    -0.43
    әрмәләр
    -0.43
     Administrativna
    -0.43
     snippetHide
    -0.42
    POSITIVE LOGITS
    +:+
    0.46
    izie
    0.42
     existing
    0.42
     Linder
    0.42
    紆
    0.41
     Loew
    0.40
     Existing
    0.40
     Pfeiffer
    0.40
     dima
    0.40
    Viitteet
    0.40
    Act Density 0.012%

    No Known Activations