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

    Neuronpedia

    INDEX
    Explanations

    Technical or instructional text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    waye
    -0.07
     REST
    -0.07
    box
    -0.07
    ated
    -0.07
    band
    -0.07
     team
    -0.07
    link
    -0.07
    REST
    -0.07
     talk
    -0.07
    ate
    -0.07
    POSITIVE LOGITS
     Homeland
    0.09
    iciary
    0.08
     inimese
    0.08
     prof
    0.08
    ૦
    0.08
     jornalista
    0.08
    ณฑ
    0.08
     суу
    0.08
    ergens
    0.08
    ॥↵↵
    0.08
    Act Density 0.001%

    No Known Activations