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

    Neuronpedia

    INDEX
    Explanations

    filename

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LM
    -0.07
    an
    -0.06
    ARTH
    -0.06
    ank
    -0.06
     encoding
    -0.06
     chat
    -0.06
     regained
    -0.06
     accepted
    -0.06
    างว
    -0.06
    /ms
    -0.06
    POSITIVE LOGITS
     Luz
    0.07
     �
    0.06
    煤
    0.06
     거의
    0.06
     Flor
    0.06
     nuestras
    0.06
    �
    0.06
    衡
    0.06
     여
    0.06
    tabl
    0.06
    Act Density 0.000%

    No Known Activations