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

    Neuronpedia

    INDEX
    Explanations

    technical writing snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ross
    -0.07
    _don
    -0.07
    ban
    -0.06
     budgets
    -0.06
    Архів
    -0.06
    byss
    -0.06
     secretary
    -0.06
    remain
    -0.06
     beg
    -0.06
    <number
    -0.06
    POSITIVE LOGITS
     Cr
    0.06
     kaynak
    0.06
    .engine
    0.06
    partment
    0.06
     plush
    0.06
    ric
    0.06
     hf
    0.06
    390
    0.06
    _PARTITION
    0.06
     �
    0.06
    Act Density 0.000%

    No Known Activations