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

    Neuronpedia

    INDEX
    Explanations

    reading up on a subject

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     związku
    -0.07
    高端
    -0.07
    ㈔
    -0.07
    יופי
    -0.07
    ספק
    -0.07
    חינוך
    -0.07
     развития
    -0.07
     Computes
    -0.06
     conducting
    -0.06
     możliwości
    -0.06
    POSITIVE LOGITS
    -talk
    0.07
    舞
    0.07
    _ENT
    0.07
    _UPDATE
    0.07
    �
    0.07
     tide
    0.07
     Năm
    0.07
    尺
    0.07
    Lights
    0.07
    PLOY
    0.06
    Act Density 0.084%

    No Known Activations