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

    Neuronpedia

    INDEX
    Explanations

    represents

    np_max-act · gemini-2.0-flash

    technical and legal terminology related to bankruptcy and litigation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Say
    -0.07
     reduction
    -0.07
     instr
    -0.06
     softly
    -0.06
    itore
    -0.06
    Tx
    -0.06
     už
    -0.06
     Hiro
    -0.06
    άντα
    -0.06
     mest
    -0.06
    POSITIVE LOGITS
     inception
    0.06
     sales
    0.06
    یمی
    0.06
    /cache
    0.06
     सच
    0.06
     anatomy
    0.06
    _COLUMNS
    0.06
    aría
    0.06
     Aurora
    0.06
     Resolver
    0.06
    Act Density 0.292%

    No Known Activations