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

    Neuronpedia

    INDEX
    Explanations

    large

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FIR
    -0.07
     viewpoint
    -0.06
     Trip
    -0.06
     compost
    -0.06
    =np
    -0.06
     Tmax
    -0.06
    (xx
    -0.06
     Develop
    -0.06
     Vision
    -0.06
     человечес
    -0.06
    POSITIVE LOGITS
     uploader
    0.06
    �
    0.06
     cf
    0.06
     sexdate
    0.06
    .Stderr
    0.06
    (textBox
    0.06
     wc
    0.06
     fiss
    0.06
    zee
    0.06
    _OLD
    0.06
    Act Density 0.015%

    No Known Activations