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

    Neuronpedia

    INDEX
    Explanations

    repeated "a"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     basically
    -0.06
     cure
    -0.06
    されて
    -0.06
     Editor
    -0.06
    atisch
    -0.06
    FullName
    -0.06
    -image
    -0.06
     metre
    -0.06
     soci
    -0.06
    grey
    -0.06
    POSITIVE LOGITS
     getClass
    0.07
     dataTable
    0.07
    ombo
    0.07
    UNCT
    0.07
    MFLOAT
    0.07
     مدر
    0.06
    .tensor
    0.06
    .utcnow
    0.06
    _Osc
    0.06
     понад
    0.06
    Act Density 0.004%

    No Known Activations