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

    Neuronpedia

    INDEX
    Explanations

    digital citizenship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vim
    -0.07
    окол
    -0.07
    벨
    -0.07
    Mel
    -0.06
    chandle
    -0.06
     предлож
    -0.06
    cus
    -0.06
    ительной
    -0.06
    _nv
    -0.06
     mustard
    -0.06
    POSITIVE LOGITS
    _array
    0.07
     분류
    0.07
     playing
    0.07
     boss
    0.07
    -office
    0.07
    ofday
    0.06
     McCoy
    0.06
    _NOTE
    0.06
     compilation
    0.06
     Minute
    0.06
    Act Density 0.036%

    No Known Activations