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

    Neuronpedia

    INDEX
    Explanations

    abstract/titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stressed
    -0.06
     pcs
    -0.06
     возраста
    -0.06
    력
    -0.06
     profund
    -0.06
     specialize
    -0.06
    avaş
    -0.06
    �
    -0.06
    abbo
    -0.06
    nesc
    -0.06
    POSITIVE LOGITS
     behaviour
    0.07
    _Source
    0.06
    ประโยชน
    0.06
    رانه
    0.06
    ระเบ
    0.06
     rejection
    0.06
    WithIdentifier
    0.06
     Locker
    0.06
     الرياض
    0.06
     Provision
    0.06
    Act Density 0.005%

    No Known Activations