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

    Neuronpedia

    INDEX
    Explanations

    technological devices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'http
    -0.07
     rightful
    -0.06
    Repository
    -0.06
     militants
    -0.06
     Νο
    -0.06
     ثلاث
    -0.06
     marrying
    -0.06
     Moves
    -0.06
     household
    -0.06
     denying
    -0.06
    POSITIVE LOGITS
    _comb
    0.07
     동안
    0.06
    ам
    0.06
    astered
    0.06
    ard
    0.06
    .squeeze
    0.06
     juga
    0.06
    .air
    0.06
     interiors
    0.06
    alg
    0.06
    Act Density 0.112%

    No Known Activations