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

    Neuronpedia

    INDEX
    Explanations

    UNC

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .act
    -0.08
    xAC
    -0.07
    겠
    -0.07
     أف
    -0.07
     Opt
    -0.07
    Sir
    -0.07
     فمن
    -0.07
    Alpha
    -0.07
     деп
    -0.06
     Phen
    -0.06
    POSITIVE LOGITS
     shortened
    0.07
    _focus
    0.07
    icana
    0.07
    halt
    0.07
    的研究
    0.06
    .HashSet
    0.06
    大涨
    0.06
    anz
    0.06
    .Sync
    0.06
    usty
    0.06
    Act Density 0.000%

    No Known Activations