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

    Neuronpedia

    INDEX
    Explanations

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Helpers
    -0.07
     bus
    -0.07
     perfect
    -0.07
     LEDs
    -0.06
     force
    -0.06
     엄
    -0.06
     оно
    -0.06
     connect
    -0.06
     find
    -0.06
     dokon
    -0.06
    POSITIVE LOGITS
    дром
    0.07
     vulnerabilities
    0.07
     Герм
    0.07
    .rev
    0.07
    etch
    0.06
    chants
    0.06
    229
    0.06
     خط
    0.06
    领
    0.06
    urable
    0.06
    Act Density 0.000%

    No Known Activations