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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cons
    -0.08
    Consider
    -0.07
    .ext
    -0.07
     initial
    -0.07
     himself
    -0.07
     force
    -0.07
    歧视
    -0.07
     Valid
    -0.07
     Sage
    -0.07
    置いて
    -0.06
    POSITIVE LOGITS
     Everybody
    0.07
     _.
    0.07
     specialties
    0.06
     (_.
    0.06
    ews
    0.06
    أكثر
    0.06
    ⏳
    0.06
    Ъ
    0.06
    ,GL
    0.06
    中新
    0.06
    Act Density 0.016%

    No Known Activations