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

    Neuronpedia

    INDEX
    Explanations

    bei

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ng
    -0.08
     that
    -0.07
    找到
    -0.07
    that
    -0.06
     PUSH
    -0.06
     нового
    -0.06
     eventually
    -0.06
     tumor
    -0.06
    .Nome
    -0.06
     SV
    -0.06
    POSITIVE LOGITS
     bei
    0.12
     beim
    0.10
     bij
    0.09
     Bei
    0.09
    Bei
    0.08
     لدي
    0.08
    beam
    0.07
    갑
    0.07
     at
    0.07
     درب
    0.07
    Act Density 0.009%

    No Known Activations