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

    Neuronpedia

    INDEX
    Explanations

    present tense and past tense verbs that indicate actions or states

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

    describing quantities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.43
    kész
    -0.43
    SequentialGroup
    -0.41
    writeHead
    -0.41
     DbType
    -0.40
    UIKit
    -0.39
    wpi
    -0.39
    Autoritní
    -0.39
    RetentionPolicy
    -0.38
    WithEmail
    -0.38
    POSITIVE LOGITS
     nakalista
    0.65
     antaranya
    0.54
     overlap
    0.48
    GIVEREF
    0.48
     diantaranya
    0.47
    antaranya
    0.47
     Muitos
    0.45
    verifyException
    0.44
     overlooked
    0.44
     Erhaltung
    0.44
    Act Density 0.054%

    No Known Activations