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

    Neuronpedia

    INDEX
    Explanations

    Technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    אות
    -0.07
    中に
    -0.07
     הן
    -0.06
     ecstatic
    -0.06
     Nil
    -0.06
     hep
    -0.06
    Hal
    -0.06
    ąc
    -0.06
    特点是
    -0.06
     pierws
    -0.06
    POSITIVE LOGITS
    养殖
    0.07
     Wildlife
    0.07
     Attorney
    0.07
    ,password
    0.07
    _dyn
    0.07
     Residential
    0.07
    ">&#
    0.07
    lexible
    0.07
    _auc
    0.07
    旅行社
    0.07
    Act Density 0.003%

    No Known Activations