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

    Neuronpedia

    INDEX
    Explanations

    code and errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cross
    -0.07
     plays
    -0.07
     <!
    -0.07
     topp
    -0.07
     Phase
    -0.07
    ッド
    -0.07
    iates
    -0.07
     responded
    -0.07
     climbing
    -0.06
     citing
    -0.06
    POSITIVE LOGITS
    столь
    0.08
     Guarantee
    0.07
    授权
    0.07
    isky
    0.07
    _SETTINGS
    0.07
    oted
    0.07
    ⽤
    0.07
    ꒰
    0.07
     cưới
    0.07
    SCALL
    0.06
    Act Density 0.421%

    No Known Activations