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

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ені
    -0.07
    มข
    -0.06
    Icon
    -0.06
    -bel
    -0.06
    Раз
    -0.06
    nj
    -0.06
    Número
    -0.06
    ури
    -0.06
     franç
    -0.06
     servis
    -0.06
    POSITIVE LOGITS
     Awake
    0.06
     생각
    0.06
     примерно
    0.06
     insult
    0.06
     eapply
    0.06
    .calls
    0.06
    calculate
    0.06
     ц
    0.06
     consumed
    0.06
    hape
    0.06
    Act Density 0.006%

    No Known Activations