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

    Neuronpedia

    INDEX
    Explanations

    Scientific publication references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    」の
    -0.06
    #----------------------------------------------------------------
    -0.06
     کی
    -0.06
    �
    -0.06
     dripping
    -0.06
    .ch
    -0.06
    InParameter
    -0.06
     руку
    -0.06
    astreet
    -0.06
    _bank
    -0.06
    POSITIVE LOGITS
    산업
    0.06
    _HW
    0.06
     rapes
    0.06
    umuz
    0.06
    .Display
    0.06
     implicitly
    0.06
     ('\
    0.06
    {{--
    0.06
    rů
    0.06
     Custom
    0.06
    Act Density 0.005%

    No Known Activations