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

    Neuronpedia

    INDEX
    Explanations

    USB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dallas
    -0.07
     Angels
    -0.06
    方向
    -0.06
    Owners
    -0.06
    ivent
    -0.06
     přij
    -0.06
    dition
    -0.06
     deadliest
    -0.06
     lidé
    -0.06
     kicker
    -0.06
    POSITIVE LOGITS
    ="${
    0.07
     Armed
    0.07
     keyed
    0.06
    .bucket
    0.06
    แท
    0.06
    .password
    0.06
    _Param
    0.06
    389
    0.06
    .Touch
    0.06
    (TokenType
    0.06
    Act Density 0.003%

    No Known Activations