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

    Neuronpedia

    INDEX
    Explanations

    2020

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;m
    -0.07
    =findViewById
    -0.07
    .keySet
    -0.07
     strands
    -0.07
    boBox
    -0.07
    ْ
    -0.07
    шь
    -0.07
    iland
    -0.06
    apter
    -0.06
     Hz
    -0.06
    POSITIVE LOGITS
    202
    0.07
    .dirname
    0.07
    inary
    0.06
     utilise
    0.06
     IOException
    0.06
     diving
    0.06
    _services
    0.06
     uncertainty
    0.06
     соч
    0.06
    lify
    0.06
    Act Density 0.018%

    No Known Activations