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

    Neuronpedia

    INDEX
    Explanations

    log

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     navigate
    -0.08
    not
    -0.07
    纠缠
    -0.07
    冲锋
    -0.07
    "All
    -0.06
     Chun
    -0.06
     Üniversites
    -0.06
     |=
    -0.06
    畅通
    -0.06
    쩠
    -0.06
    POSITIVE LOGITS
    امي
    0.08
     dak
    0.08
     philosophy
    0.07
    iem
    0.07
     bổ
    0.07
     dereg
    0.07
    -dem
    0.07
    craper
    0.07
    俏
    0.07
    胃肠
    0.06
    Act Density 0.011%

    No Known Activations