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

    Neuronpedia

    INDEX
    Explanations

    factors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _brightness
    -0.08
     Discussions
    -0.07
    kiye
    -0.06
     implementation
    -0.06
     wager
    -0.06
    implementation
    -0.06
     decisions
    -0.06
     alc
    -0.06
    straction
    -0.06
     guilt
    -0.06
    POSITIVE LOGITS
     dahi
    0.07
     SPECIAL
    0.07
     popul
    0.07
    ocrine
    0.07
    ,w
    0.06
     stav
    0.06
     SM
    0.06
    ordum
    0.06
     Filter
    0.06
    chure
    0.06
    Act Density 0.007%

    No Known Activations