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

    Neuronpedia

    INDEX
    Explanations

    smile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    docs
    -0.07
     prov
    -0.07
     bacter
    -0.07
    spec
    -0.07
     Vapor
    -0.07
     Dangerous
    -0.07
     invalid
    -0.07
    _che
    -0.06
    _gain
    -0.06
    _dev
    -0.06
    POSITIVE LOGITS
     smile
    0.08
     улыб
    0.07
    .BooleanField
    0.07
    ी।↵
    0.06
     Smile
    0.06
    ительность
    0.06
    _InternalArray
    0.06
     memnun
    0.06
    ोल
    0.06
    SL
    0.06
    Act Density 0.008%

    No Known Activations