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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Judge
    -0.08
    .false
    -0.07
     Vox
    -0.07
     Tray
    -0.07
    .flag
    -0.07
     ASM
    -0.07
    农副
    -0.07
    ň
    -0.07
     Sheriff
    -0.07
     RAF
    -0.07
    POSITIVE LOGITS
    _ratio
    0.08
     Gol
    0.07
     losing
    0.06
    ping
    0.06
    光纤
    0.06
    全局
    0.06
     пут
    0.06
    拉
    0.06
    ":[
    0.06
    (function
    0.06
    Act Density 0.002%

    No Known Activations