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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    альное
    -0.08
    thren
    -0.07
    race
    -0.07
    sampling
    -0.06
    asel
    -0.06
    brtc
    -0.06
    .range
    -0.06
     Elections
    -0.06
     Coupe
    -0.06
    70
    -0.06
    POSITIVE LOGITS
    hdr
    0.07
     getChild
    0.06
     Gujar
    0.06
     usted
    0.06
    -program
    0.06
     nd
    0.06
    Fixed
    0.06
     duk
    0.06
     tranquil
    0.06
     ocor
    0.06
    Act Density 0.045%

    No Known Activations