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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dictionary
    -0.06
    /layouts
    -0.06
     DIAG
    -0.06
     montage
    -0.06
    (li
    -0.06
     이를
    -0.06
    .FileWriter
    -0.06
    cot
    -0.05
     nesting
    -0.05
    .monitor
    -0.05
    POSITIVE LOGITS
     privat
    0.07
    -price
    0.07
    ohn
    0.07
     буду
    0.07
     infinity
    0.06
    "],"
    0.06
     torture
    0.06
     ces
    0.06
    izard
    0.06
     proceso
    0.06
    Act Density 0.007%

    No Known Activations