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

    Neuronpedia

    INDEX
    Explanations

    star

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بـ
    -0.06
     ulus
    -0.06
     पड
    -0.06
     NOP
    -0.06
     �
    -0.06
     ridicule
    -0.06
    看着
    -0.06
     curb
    -0.06
    东省
    -0.06
     technolog
    -0.06
    POSITIVE LOGITS
    afka
    0.07
    jk
    0.06
    TM
    0.06
    І
    0.06
    _resp
    0.06
    /global
    0.06
    Nx
    0.06
     LP
    0.06
    _af
    0.06
    ثار
    0.06
    Act Density 0.002%

    No Known Activations