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

    Neuronpedia

    INDEX
    Explanations

    pandas dataframes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DEAL
    -0.08
    gages
    -0.07
    مزيد
    -0.06
    ﮐ
    -0.06
    名叫
    -0.06
    olving
    -0.06
    实实在
    -0.06
    leasing
    -0.06
    csrf
    -0.06
    عاط
    -0.06
    POSITIVE LOGITS
     conforme
    0.08
    /)
    0.07
    /logs
    0.07
    Implemented
    0.07
     Sala
    0.07
    Superview
    0.07
    /Branch
    0.07
     Roe
    0.07
    /provider
    0.07
     sala
    0.07
    Act Density 0.029%

    No Known Activations