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

    Neuronpedia

    INDEX
    Explanations

    attracting new fans/users

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finely
    -0.07
    ary
    -0.06
    ruptcy
    -0.06
    stu
    -0.06
     Cave
    -0.06
    amin
    -0.06
    azole
    -0.06
    ождение
    -0.06
     WLAN
    -0.06
     forgive
    -0.06
    POSITIVE LOGITS
     coordinator
    0.07
     виготов
    0.07
     мужчин
    0.06
     abruptly
    0.06
     Angeles
    0.06
    _PAR
    0.06
     دنبال
    0.06
     своим
    0.06
    _DICT
    0.06
    PRESENT
    0.06
    Act Density 0.068%

    No Known Activations