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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _rpc
    -0.07
     docker
    -0.07
     oxygen
    -0.07
    <char
    -0.07
     culo
    -0.07
    ắn
    -0.06
    nodes
    -0.06
    化肥
    -0.06
    📨
    -0.06
     thừa
    -0.06
    POSITIVE LOGITS
     Kosten
    0.07
     Opportunities
    0.07
    TING
    0.07
    会使
    0.06
    멤
    0.06
     FR
    0.06
     percent
    0.06
    .progressBar
    0.06
    多い
    0.06
    _product
    0.06
    Act Density 0.002%

    No Known Activations