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

    Neuronpedia

    INDEX
    Explanations

    exercise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adicion
    -0.07
     ن
    -0.07
     חדר
    -0.07
    iêu
    -0.07
     IMM
    -0.07
     /^[
    -0.07
    Discovery
    -0.06
    ולה
    -0.06
    都被
    -0.06
    (cube
    -0.06
    POSITIVE LOGITS
    调节
    0.08
    (None
    0.08
    _encoding
    0.07
    elay
    0.07
    下さい
    0.07
    computer
    0.07
    阶段
    0.06
    _stock
    0.06
    PILE
    0.06
    🕑
    0.06
    Act Density 0.017%

    No Known Activations