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

    Neuronpedia

    INDEX
    Explanations

    13

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -medium
    -0.06
    /inc
    -0.06
    fect
    -0.06
     чином
    -0.06
    �
    -0.06
    fs
    -0.06
    /workspace
    -0.06
    (btn
    -0.06
    ultz
    -0.06
     esse
    -0.06
    POSITIVE LOGITS
    whether
    0.06
    งเป
    0.06
     madrid
    0.06
    帕
    0.06
     Moodle
    0.06
    เช
    0.06
    ADB
    0.06
     GER
    0.06
     เด
    0.06
    URA
    0.06
    Act Density 0.005%

    No Known Activations