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

    Neuronpedia

    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Στα
    -0.06
     refactor
    -0.06
     compens
    -0.06
    라마
    -0.06
    _SCRIPT
    -0.06
     EL
    -0.06
    飯
    -0.06
     DependencyProperty
    -0.06
     キ
    -0.06
     عنه
    -0.06
    POSITIVE LOGITS
    운드
    0.07
    _article
    0.07
     Venice
    0.07
    なくな
    0.07
     méth
    0.06
     плав
    0.06
     activism
    0.06
    _matched
    0.06
    CLUDING
    0.06
    yen
    0.06
    Act Density 0.010%

    No Known Activations