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

    Neuronpedia

    INDEX
    Explanations

    Recency, Frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scissors
    -0.08
     clang
    -0.07
     gothic
    -0.07
    clang
    -0.07
    beaut
    -0.07
    Vak
    -0.07
     brave
    -0.07
     زیب
    -0.07
     trenches
    -0.07
     крас
    -0.07
    POSITIVE LOGITS
    充值
    0.11
     cohorts
    0.10
    	customer
    0.10
    累计
    0.10
     고객
    0.10
     जिन्होंने
    0.10
     fidél
    0.10
    营销
    0.09
    /customer
    0.09
     ग्राहक
    0.09
    Act Density 0.015%

    No Known Activations