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

    Neuronpedia

    INDEX
    Explanations

    mixed technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     listar
    -0.07
    Speaking
    -0.07
    eko
    -0.06
    㳇
    -0.06
     migli
    -0.06
    مكة
    -0.06
    eken
    -0.06
    /Image
    -0.06
    toLocale
    -0.06
     volver
    -0.06
    POSITIVE LOGITS
     Issue
    0.08
     creds
    0.07
     wastes
    0.07
    琄
    0.07
    ASSWORD
    0.07
     Pix
    0.06
    💯
    0.06
    utter
    0.06
    舭
    0.06
    唤
    0.06
    Act Density 0.026%

    No Known Activations