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

    Neuronpedia

    INDEX
    Explanations

    GH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ancer
    -0.07
     veel
    -0.06
     real
    -0.06
     день
    -0.06
     peux
    -0.06
    _man
    -0.06
    olid
    -0.06
    ари
    -0.06
    _guid
    -0.06
    inge
    -0.06
    POSITIVE LOGITS
    ahaha
    0.07
     BufferedWriter
    0.07
     brace
    0.07
    Ess
    0.07
    ()"↵
    0.06
    ($(
    0.06
    .q
    0.06
    hyper
    0.06
     violently
    0.06
    (UInt
    0.06
    Act Density 0.000%

    No Known Activations