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

    Neuronpedia

    INDEX
    Explanations

    Brooklyn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    licant
    -0.07
    =====↵
    -0.07
    _argument
    -0.07
    _${
    -0.06
    必要
    -0.06
     Gods
    -0.06
     Ferdinand
    -0.06
    _DELETED
    -0.06
    २०
    -0.06
     "{{
    -0.06
    POSITIVE LOGITS
     وك
    0.08
     Brooklyn
    0.07
    ylan
    0.07
     Brook
    0.07
     DERP
    0.07
    gent
    0.06
     alf
    0.06
     ven
    0.06
     disap
    0.06
     трен
    0.06
    Act Density 0.002%

    No Known Activations