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

    Neuronpedia

    INDEX
    Explanations

    expressions of exception or contrast

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

    except for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     via
    -0.39
     Information
    -0.39
     Extremely
    -0.37
    Information
    -0.37
     Fenster
    -0.36
     provides
    -0.36
     providing
    -0.36
     previously
    -0.36
     прият
    -0.35
     extremadamente
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    0.69
     للمعارف
    0.69
    WriteTagHelper
    0.65
     שוליים
    0.65
    UserScript
    0.64
    elemField
    0.63
    SequentialGroup
    0.61
    __':
    0.60
     nonUne
    0.59
    MigrationBuilder
    0.57
    Act Density 0.026%

    No Known Activations