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

    Neuronpedia

    INDEX
    Explanations

    disclaimers or avoiding engagement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وز
    -0.07
     немного
    -0.07
     united
    -0.07
     --------------------------------
    -0.07
    沟
    -0.07
     lui
    -0.07
     тор
    -0.07
     Eden
    -0.07
    burn
    -0.06
     "></
    -0.06
    POSITIVE LOGITS
     layoutManager
    0.06
     Sharing
    0.06
     bourgeoisie
    0.06
     ACPI
    0.06
     Troll
    0.06
    .timeline
    0.06
     rewrite
    0.06
    pector
    0.06
     없어
    0.05
     prostitu
    0.05
    Act Density 0.017%

    No Known Activations