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

    Neuronpedia

    INDEX
    Explanations

    Withdrawal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stacks
    -0.08
    awala
    -0.07
    )-
    -0.07
    “-
    -0.07
    יון
    -0.07
    Wildcard
    -0.07
     Mine
    -0.07
    '-
    -0.07
    -name
    -0.07
     cuisson
    -0.07
    POSITIVE LOGITS
     الاجتماعية
    0.10
    /social
    0.10
     социальных
    0.10
     المجتمع
    0.10
     sociaal
    0.09
     social
    0.09
    social
    0.09
    困
    0.09
     സാമൂഹ
    0.09
     социальной
    0.09
    Act Density 0.012%

    No Known Activations