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

    Neuronpedia

    INDEX
    Explanations

    reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anol
    -0.08
     représentant
    -0.08
    geois
    -0.07
     representing
    -0.07
     hãng
    -0.07
     food
    -0.07
     తొలి
    -0.07
     hobby
    -0.07
     herb
    -0.07
     představ
    -0.07
    POSITIVE LOGITS
     Refer
    0.13
     referencing
    0.13
    Refer
    0.12
     REFERENCES
    0.12
    引用
    0.12
     referencias
    0.12
    .reference
    0.12
     referenced
    0.11
    References
    0.11
     참
    0.11
    Act Density 0.022%

    No Known Activations