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

    Neuronpedia

    INDEX
    Explanations

    low

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dateTime
    -0.07
     prosecute
    -0.07
    雅
    -0.07
     Up
    -0.07
    acebook
    -0.07
     Reb
    -0.06
     Software
    -0.06
    _exe
    -0.06
    ější
    -0.06
     hacked
    -0.06
    POSITIVE LOGITS
    コ
    0.06
     шаг
    0.06
     hg
    0.06
     narrowed
    0.06
     llegar
    0.05
    igham
    0.05
     lob
    0.05
     advisable
    0.05
     taj
    0.05
    /max
    0.05
    Act Density 0.021%

    No Known Activations