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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     undue
    -0.06
    indle
    -0.06
    Wh
    -0.06
     Dry
    -0.06
    Wil
    -0.06
    ragment
    -0.06
     Language
    -0.06
    _io
    -0.06
    Nous
    -0.06
     dây
    -0.06
    POSITIVE LOGITS
    .BooleanField
    0.07
    Aligned
    0.06
     totaling
    0.06
    _CONFIGURATION
    0.06
     شد
    0.06
     Someone
    0.06
    gather
    0.06
     Palestinian
    0.06
     purified
    0.06
     řed
    0.06
    Act Density 0.199%

    No Known Activations