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

    Neuronpedia

    INDEX
    Explanations

    bras

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patrol
    -0.07
    <DateTime
    -0.07
    ober
    -0.07
     socialist
    -0.07
     convinc
    -0.06
     congress
    -0.06
     fencing
    -0.06
     system
    -0.06
    type
    -0.06
     ditch
    -0.06
    POSITIVE LOGITS
    백
    0.06
     IM
    0.06
    ilendir
    0.06
     meş
    0.06
    edula
    0.06
     мають
    0.06
    497
    0.06
     등을
    0.06
    افع
    0.06
     تع
    0.06
    Act Density 0.035%

    No Known Activations