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

    Neuronpedia

    INDEX
    Explanations

    phrases containing both "to" and "with" where a comparison is being made

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.96
    FormTagHelper
    -0.78
    Hentet
    -0.71
    enumi
    -0.65
     ExecuteAsync
    -0.64
    })`
    -0.63
    \{\\
    -0.63
    twimg
    -0.61
    .*")]
    -0.61
    %)$
    -0.59
    POSITIVE LOGITS
     compares
    0.60
     analogous
    0.58
    Ful
    0.57
    ::_('
    0.56
     ähnlichen
    0.55
     Protección
    0.55
    fuls
    0.54
     similar
    0.52
     Krä
    0.52
     occaf
    0.51
    Act Density 0.025%

    No Known Activations