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

    Neuronpedia

    INDEX
    Explanations

    Genes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    licher
    -0.07
     tree
    -0.07
     wie
    -0.06
    ogram
    -0.06
     as
    -0.06
    /back
    -0.06
     eg
    -0.06
     prophet
    -0.06
    reply
    -0.06
     kn
    -0.06
    POSITIVE LOGITS
    CLU
    0.08
     Â
    0.07
    ivent
    0.07
    ⁿ
    0.07
    렝
    0.07
    鼓
    0.06
    劳动
    0.06
     hazards
    0.06
    _ax
    0.06
    bor
    0.06
    Act Density 0.082%

    No Known Activations