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

    Neuronpedia

    INDEX
    Explanations

    action verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Quiet
    -0.08
     Wie
    -0.07
    emony
    -0.07
     Neil
    -0.07
     repetition
    -0.07
    Mas
    -0.07
     emploi
    -0.07
    _fmt
    -0.07
     Monte
    -0.07
     Danny
    -0.07
    POSITIVE LOGITS
    filer
    0.08
     fick
    0.07
    ziehung
    0.07
    Health
    0.07
     handler
    0.07
    촛
    0.07
     Kang
    0.06
    croll
    0.06
     Possible
    0.06
     Gauss
    0.06
    Act Density 0.051%

    No Known Activations