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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Aggressive
    -0.07
    	next
    -0.07
    .PLL
    -0.06
    curacy
    -0.06
    %.
    -0.06
    Esc
    -0.06
     lev
    -0.06
    .FLAG
    -0.06
    数量
    -0.06
     forwards
    -0.06
    POSITIVE LOGITS
    ifikasi
    0.07
    utf
    0.07
    -cloud
    0.06
     userProfile
    0.06
    IBUTES
    0.06
     (↵↵
    0.06
     رمز
    0.06
     раб
    0.06
    цем
    0.06
    .states
    0.06
    Act Density 0.081%

    No Known Activations