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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pixel
    -0.06
     lunch
    -0.06
    446
    -0.06
    talk
    -0.06
     ppm
    -0.06
    inity
    -0.06
    they
    -0.06
    test
    -0.06
    _nm
    -0.06
    jer
    -0.06
    POSITIVE LOGITS
    .Of
    0.07
     autoFocus
    0.07
     Of
    0.07
     Mell
    0.07
    ительность
    0.06
     caveat
    0.06
    兹
    0.06
     Fakültesi
    0.06
    /modules
    0.06
     امکان
    0.06
    Act Density 0.004%

    No Known Activations