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

    Neuronpedia

    INDEX
    Explanations

    references to cosmopolitanism or cosmopolitan settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    cosmopolitan and Cosmo followed by identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.63
    __':
    -0.55
     Ucrania
    -0.54
     fallu
    -0.49
    __":
    -0.47
    mergeFrom
    -0.47
     reliever
    -0.47
    DockStyle
    -0.44
    ();)
    -0.43
     doença
    -0.42
    POSITIVE LOGITS
     cosmopolitan
    2.08
    mopolitan
    2.03
     Cosmopolitan
    1.84
    mopol
    1.13
     Cosmo
    0.91
     cosmo
    0.87
    politan
    0.81
    Cosmo
    0.78
    cosmo
    0.66
     sophisticated
    0.63
    Act Density 0.002%

    No Known Activations