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

    Neuronpedia

    INDEX
    Explanations

    Halo/Spartan context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Depend
    -0.07
     assh
    -0.07
     Premium
    -0.06
     Conscious
    -0.06
     ironic
    -0.06
     taxed
    -0.06
    	Random
    -0.06
    (Location
    -0.06
     Interviews
    -0.06
     recoil
    -0.06
    POSITIVE LOGITS
    CHAR
    0.07
    ्यवस
    0.07
     raspberry
    0.07
    @property
    0.06
    _Em
    0.06
    �
    0.06
     regimen
    0.06
    ₀
    0.06
     Wein
    0.06
     Theodore
    0.06
    Act Density 0.008%

    No Known Activations