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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CR
    -0.08
    하고
    -0.07
    יופי
    -0.07
    แช
    -0.07
     trabalho
    -0.07
     erotico
    -0.07
    Normalized
    -0.07
     JMP
    -0.07
     Crash
    -0.07
    RS
    -0.07
    POSITIVE LOGITS
    .until
    0.08
     Quinn
    0.07
    (!(
    0.07
     (_.
    0.07
    \Plugin
    0.07
    (links
    0.07
    okin
    0.07
    形势
    0.07
    akening
    0.07
     фиг
    0.06
    Act Density 0.020%

    No Known Activations