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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating easiness or simplicity in tasks or concepts

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

    easy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DataMember
    -0.51
    mapStateToProps
    -0.47
     capucha
    -0.46
     henkil
    -0.45
    Nazionale
    -0.45
     valign
    -0.44
    HostException
    -0.42
    migrationBuilder
    -0.42
    labelControl
    -0.42
     Tagore
    -0.41
    POSITIVE LOGITS
    easy
    1.76
    Easy
    1.73
     Easy
    1.63
     easy
    1.59
     EASY
    1.52
    EASY
    1.46
    easier
    1.16
     fáciles
    1.15
     Easier
    1.07
    Easier
    1.07
    Act Density 0.015%

    No Known Activations