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

    Neuronpedia

    INDEX
    Explanations

    inventions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .be
    -0.07
     무료
    -0.07
     quyền
    -0.07
     Peer
    -0.06
     ese
    -0.06
     watchdog
    -0.06
     türlü
    -0.06
     theres
    -0.06
    ufig
    -0.06
     Helsinki
    -0.06
    POSITIVE LOGITS
    imu
    0.07
    των
    0.07
    onation
    0.06
    Completion
    0.06
    istency
    0.06
     مختلف
    0.06
    ToInt
    0.06
    Shot
    0.06
    ريك
    0.06
     fou
    0.06
    Act Density 0.052%

    No Known Activations