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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accus
    -0.07
    ふ
    -0.07
     MAV
    -0.07
    fft
    -0.06
     IC
    -0.06
    chemas
    -0.06
     Leap
    -0.06
     flakes
    -0.06
     findings
    -0.06
    icle
    -0.06
    POSITIVE LOGITS
    博物
    0.07
     vir
    0.06
    вок
    0.06
    단체
    0.06
    issy
    0.06
    tility
    0.06
     elemento
    0.06
    _processing
    0.06
    _VE
    0.06
     тяж
    0.06
    Act Density 0.007%

    No Known Activations