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

    Neuronpedia

    INDEX
    Explanations

    human states of being

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     하루
    -0.06
     captivating
    -0.06
     ا
    -0.06
    HeaderInSection
    -0.06
    inch
    -0.06
     сест
    -0.06
    .PREFERRED
    -0.06
     intriguing
    -0.06
     Maria
    -0.06
     děti
    -0.06
    POSITIVE LOGITS
    мат
    0.07
     Bow
    0.06
     BaseActivity
    0.06
    ISED
    0.06
    _PACK
    0.06
    ACIÓN
    0.06
    _locations
    0.06
     complain
    0.06
    umsuz
    0.06
    -package
    0.06
    Act Density 0.238%

    No Known Activations