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

    Neuronpedia

    INDEX
    Explanations

    Walls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    立马
    -0.09
    (letter
    -0.07
    <Float
    -0.07
    Surv
    -0.07
     chiều
    -0.07
    🏯
    -0.07
    (Void
    -0.07
     pdf
    -0.07
     ultimo
    -0.06
    tık
    -0.06
    POSITIVE LOGITS
    사업
    0.07
    fect
    0.07
    拍拍
    0.06
     לפתוח
    0.06
    INSERT
    0.06
    perfect
    0.06
    乐队
    0.06
     Platform
    0.06
    卫健委
    0.06
     blasting
    0.06
    Act Density 0.118%

    No Known Activations