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

    Neuronpedia

    INDEX
    Explanations

    little

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theatre
    -0.07
    かない
    -0.07
    -or
    -0.07
     brewery
    -0.06
     sexo
    -0.06
    ुआत
    -0.06
     bus
    -0.06
    riger
    -0.06
     �
    -0.06
    $value
    -0.06
    POSITIVE LOGITS
     свою
    0.07
     stocks
    0.07
    xFD
    0.06
    lena
    0.06
     سری
    0.06
    \Response
    0.06
    itunes
    0.06
     >",
    0.06
     perv
    0.06
    fieldName
    0.06
    Act Density 0.000%

    No Known Activations