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

    Neuronpedia

    INDEX
    Explanations

    Japanese characters and punctuation used in written language

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

    mixed language and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     móvel
    -0.42
     capitales
    -0.40
     Hinsicht
    -0.39
     conversaciones
    -0.38
     Existenz
    -0.36
     honte
    -0.36
     iliş
    -0.35
     traffico
    -0.35
     skóra
    -0.35
     toiminta
    -0.35
    POSITIVE LOGITS
    opress
    0.57
    EDEFAULT
    0.57
    aarrggbb
    0.56
     defaultstate
    0.53
    GraphicsUnit
    0.52
    UnusedPrivate
    0.52
    IOLOGY
    0.50
    ilateral
    0.50
    entran
    0.49
    הערות
    0.49
    Act Density 0.336%

    No Known Activations