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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     study
    -0.06
    ckill
    -0.06
    .stamp
    -0.06
     spine
    -0.06
     translations
    -0.06
    cond
    -0.06
    _No
    -0.06
     مز
    -0.06
     sept
    -0.06
     gh
    -0.06
    POSITIVE LOGITS
    )+
    0.07
     ε�
    0.07
    _php
    0.07
     endwhile
    0.06
    (parts
    0.06
     已
    0.06
    .Text
    0.06
    /Resources
    0.06
     Rails
    0.06
    ucose
    0.06
    Act Density 0.023%

    No Known Activations