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

    Neuronpedia

    INDEX
    Explanations

    knot theory/homology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    빚
    -0.07
    مطار
    -0.07
     ejac
    -0.07
    arel
    -0.07
     Become
    -0.07
     Grove
    -0.06
     만나
    -0.06
    omas
    -0.06
    盆
    -0.06
    VP
    -0.06
    POSITIVE LOGITS
     וכי
    0.08
    兒童
    0.07
    (issue
    0.07
     ACLU
    0.07
    ��
    0.07
    ,ll
    0.07
     판단
    0.07
    になる
    0.07
    unless
    0.07
    出现问题
    0.07
    Act Density 0.008%

    No Known Activations