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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with identifiers and links, particularly in a structured data format

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

    Numbers or small caps formatting

    np_acts-logits-general · gemini-2.0-flash

    small-caps names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cognac
    -0.81
     Cough
    -0.76
     cognac
    -0.74
     Elijah
    -0.73
     Tuli
    -0.72
     Reinh
    -0.72
     Dubois
    -0.71
     Ariel
    -0.71
     Knot
    -0.69
     Boogie
    -0.68
    POSITIVE LOGITS
     Matheson
    0.67
     Allison
    0.59
    jessica
    0.58
     Wint
    0.58
    Allison
    0.57
     PLOS
    0.56
     Dickens
    0.55
     jessica
    0.55
     Eck
    0.53
    esson
    0.53
    Act Density 1.646%

    No Known Activations