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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TOO
    -0.08
    骍
    -0.07
     *)__
    -0.07
    铽
    -0.07
    IRTUAL
    -0.07
    מדבר
    -0.07
     sehr
    -0.07
    connect
    -0.07
     Virgin
    -0.07
     devast
    -0.07
    POSITIVE LOGITS
     zg
    0.08
     IMD
    0.07
    <Model
    0.07
    לכאורה
    0.07
     ik
    0.07
     Manila
    0.07
     Miami
    0.07
    は
    0.06
    循
    0.06
    _userid
    0.06
    Act Density 0.091%

    No Known Activations