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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     niños
    -0.06
    监
    -0.06
    .FC
    -0.06
    PLL
    -0.06
    말
    -0.06
     Keys
    -0.06
    helm
    -0.06
     Collapse
    -0.06
    credible
    -0.06
    blind
    -0.06
    POSITIVE LOGITS
    ламент
    0.07
     арми
    0.07
     pomáh
    0.06
     edilir
    0.06
     ног
    0.06
    .progressBar
    0.06
    (dr
    0.06
     oath
    0.06
     sparks
    0.06
    houses
    0.06
    Act Density 0.026%

    No Known Activations