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

    Neuronpedia

    INDEX
    Explanations

    speculate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     applauded
    -0.07
     cleanliness
    -0.06
     rés
    -0.06
     hus
    -0.06
     courteous
    -0.06
     crippled
    -0.06
    休
    -0.06
    マン
    -0.06
     customizable
    -0.06
     purified
    -0.06
    POSITIVE LOGITS
     speculation
    0.12
     speculate
    0.10
     speculated
    0.09
    xFFFFFF
    0.07
     ---------------------------------------------------------------------------↵
    0.07
     Clause
    0.07
    Chocolate
    0.07
     theor
    0.07
    하지
    0.06
     disclosures
    0.06
    Act Density 0.007%

    No Known Activations