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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Helper
    -0.07
    医疗
    -0.07
    -ray
    -0.07
    _pair
    -0.07
     salari
    -0.07
    _$_
    -0.07
    _begin
    -0.07
     sensations
    -0.07
     Einsatz
    -0.06
     myfile
    -0.06
    POSITIVE LOGITS
     old
    0.08
     percent
    0.08
    .hours
    0.07
     Sept
    0.07
    要比
    0.07
     cops
    0.07
    ?'↵↵
    0.07
    HasColumnType
    0.07
     scrolls
    0.06
    כנים
    0.06
    Act Density 0.003%

    No Known Activations