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

    Neuronpedia

    INDEX
    Explanations

    programming questions/edits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Notes
    -0.07
    /support
    -0.07
    לחץ
    -0.07
    �
    -0.07
    mg
    -0.07
    Rose
    -0.07
     Third
    -0.07
     TOOL
    -0.06
     Axel
    -0.06
    _firstname
    -0.06
    POSITIVE LOGITS
    alık
    0.07
     receptions
    0.07
    ומי
    0.07
    חינ
    0.07
    веден
    0.07
    pletion
    0.07
     wors
    0.07
    大户
    0.07
    缝
    0.07
    妥
    0.06
    Act Density 0.043%

    No Known Activations