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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with providing mathematical proofs or logical reasoning

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eless
    -0.06
    vfs
    -0.06
    isco
    -0.06
    Contained
    -0.06
    onde
    -0.06
    opot
    -0.06
    Ãło
    -0.06
    celed
    -0.06
    atorio
    -0.06
    arden
    -0.06
    POSITIVE LOGITS
     things
    0.08
     conditions
    0.08
     conclusions
    0.07
     true
    0.07
     statement
    0.07
     statements
    0.07
     such
    0.07
     something
    0.06
     conclusion
    0.06
     Mour
    0.06
    Act Density 0.093%

    No Known Activations