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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verschill
    -0.07
    _BGR
    -0.07
    有针对性
    -0.06
    aven
    -0.06
    联赛
    -0.06
     vaccinated
    -0.06
    -0.06
     Pv
    -0.06
    TypeId
    -0.06
    修正
    -0.06
    POSITIVE LOGITS
     encuentra
    0.08
     Ones
    0.07
    oyo
    0.07
     ruth
    0.07
     być
    0.07
    _SCOPE
    0.07
     Rubin
    0.07
    engkap
    0.06
     era
    0.06
     originated
    0.06
    Act Density 0.025%

    No Known Activations