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

    Neuronpedia

    INDEX
    Explanations

    Phone features

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #ab
    -0.07
    orda
    -0.07
    равиль
    -0.06
    Cat
    -0.06
     published
    -0.06
    move
    -0.06
    CBD
    -0.06
     Yours
    -0.06
     reinforces
    -0.06
     packing
    -0.06
    POSITIVE LOGITS
     blackmail
    0.07
     uz
    0.07
    /effects
    0.07
     <!--[
    0.07
     negligent
    0.07
     indir
    0.07
    URLException
    0.07
    Misc
    0.06
    _coeffs
    0.06
    ycastle
    0.06
    Act Density 0.015%

    No Known Activations