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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     simultaneous
    -0.07
    quan
    -0.07
     eruption
    -0.07
     mediated
    -0.07
     Click
    -0.07
     mah
    -0.07
     lint
    -0.06
    ülük
    -0.06
     vivo
    -0.06
     февраля
    -0.06
    POSITIVE LOGITS
    Instrument
    0.06
     indis
    0.06
    abcdefgh
    0.06
     konci
    0.06
     Mavericks
    0.06
    .Question
    0.06
     EVAL
    0.06
     comple
    0.06
     multiline
    0.06
     @"↵
    0.06
    Act Density 0.331%

    No Known Activations