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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _locale
    -0.06
    곤
    -0.06
     Qual
    -0.06
    EOS
    -0.06
    Slots
    -0.06
    du
    -0.06
     loaf
    -0.06
    -seeking
    -0.06
    aniem
    -0.06
    ainment
    -0.06
    POSITIVE LOGITS
    isdiction
    0.08
    (日
    0.07
     Franti
    0.07
     پیوند
    0.06
     Jenna
    0.06
    _score
    0.06
    :function
    0.06
    .ext
    0.06
    nP
    0.06
    charged
    0.06
    Act Density 0.005%

    No Known Activations