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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .In
    -0.07
    riterion
    -0.06
     dissemination
    -0.06
    DMA
    -0.06
     MD
    -0.06
    _NONNULL
    -0.06
     terse
    -0.06
    	attack
    -0.06
     ald
    -0.06
     dic
    -0.06
    POSITIVE LOGITS
    (bot
    0.08
    ละคร
    0.07
     The
    0.07
    apiro
    0.07
    /foo
    0.06
     the
    0.06
     П
    0.06
    The
    0.06
    μπ
    0.06
     MOT
    0.06
    Act Density 0.056%

    No Known Activations