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

    Neuronpedia

    INDEX
    Explanations

    say "("

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _name
    -0.07
     Toxic
    -0.07
    햋
    -0.07
     Smash
    -0.07
    艺
    -0.07
    eny
    -0.07
    年轻
    -0.07
    ตรวจ
    -0.06
    保险
    -0.06
    $/
    -0.06
    POSITIVE LOGITS
    contract
    0.07
     declines
    0.07
    ffffffff
    0.07
    _,↵
    0.07
    fab
    0.07
    	fn
    0.07
    dispose
    0.07
     compat
    0.07
    เป
    0.06
    Widget
    0.06
    Act Density 0.004%

    No Known Activations