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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    สล
    -0.06
     najle
    -0.06
     Neh
    -0.06
    aturdays
    -0.06
     Eden
    -0.06
    utschen
    -0.06
     WPARAM
    -0.06
    (jScrollPane
    -0.06
    eczy
    -0.06
    benh
    -0.06
    POSITIVE LOGITS
     Observ
    0.09
     Phot
    0.08
     of
    0.08
     i
    0.07
    To
    0.07
     A
    0.07
    OULD
    0.07
     I
    0.07
    _INFO
    0.07
     Pet
    0.07
    Act Density 0.020%

    No Known Activations