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

    Neuronpedia

    INDEX
    Explanations

    choices and decisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    呈
    -0.08
    -vertical
    -0.07
     insured
    -0.07
    apk
    -0.07
    templ
    -0.07
    统统
    -0.07
    첨
    -0.07
    (dir
    -0.07
     mail
    -0.07
    Ÿ
    -0.07
    POSITIVE LOGITS
     cancell
    0.07
     contrary
    0.07
    _counters
    0.07
     Spar
    0.07
    ence
    0.07
     fran
    0.07
     suas
    0.07
     sake
    0.07
    0.06
    _attention
    0.06
    Act Density 0.135%

    No Known Activations