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

    Neuronpedia

    INDEX
    Explanations

    Personal reflections/experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    采取
    -0.07
    Ú
    -0.07
    十七条
    -0.07
     tiene
    -0.07
    该院
    -0.07
     فإذا
    -0.06
    .telegram
    -0.06
    -F
    -0.06
     בגין
    -0.06
     specimen
    -0.06
    POSITIVE LOGITS
    וז
    0.07
    ledon
    0.07
    콕
    0.07
     sql
    0.07
    bill
    0.06
    征信
    0.06
    (all
    0.06
     Infect
    0.06
    gett
    0.06
    _end
    0.06
    Act Density 0.150%

    No Known Activations