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

    Neuronpedia

    INDEX
    Explanations

    methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เคล
    -0.07
    _RADIO
    -0.06
     CNBC
    -0.06
     Confederate
    -0.06
     Socialist
    -0.06
    -le
    -0.06
     Nacht
    -0.06
    Icon
    -0.06
    OTS
    -0.06
    Prop
    -0.06
    POSITIVE LOGITS
    _go
    0.06
    .logs
    0.06
    0.06
     Dân
    0.06
    prites
    0.06
     outlet
    0.06
     constrain
    0.06
     مع
    0.06
    >this
    0.06
    are
    0.06
    Act Density 0.053%

    No Known Activations