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

    Neuronpedia

    INDEX
    Explanations

    Code licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Manifest
    -0.07
    isp
    -0.07
     הלב
    -0.07
    ثل
    -0.07
    ыв
    -0.07
    alt
    -0.06
    omp
    -0.06
    -threat
    -0.06
    ぁ
    -0.06
     unw
    -0.06
    POSITIVE LOGITS
     '*
    0.08
    #'
    0.08
    *'
    0.08
     "
    0.08
    (++
    0.08
     Relatives
    0.08
    끈
    0.08
     mistakenly
    0.08
     ';'
    0.07
    polit
    0.07
    Act Density 2.732%

    No Known Activations