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

    Neuronpedia

    INDEX
    Explanations

    neatness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     چند
    -0.07
     найбільш
    -0.07
    _HEAD
    -0.07
    운드
    -0.07
     문서
    -0.07
     SUBSTITUTE
    -0.07
    ----------↵↵
    -0.06
     "<
    -0.06
    (ERROR
    -0.06
    **
    -0.06
    POSITIVE LOGITS
     neat
    0.08
     Arts
    0.06
    edor
    0.06
    etta
    0.06
    CK
    0.06
    -ton
    0.06
     Kick
    0.06
    ist
    0.06
     Vuex
    0.06
    Unt
    0.06
    Act Density 0.006%

    No Known Activations