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

    Neuronpedia

    INDEX
    Explanations

    punctuated endings and references to time or sequences in narratives

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

    stopped or started

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     osob
    -0.41
     coordinación
    -0.40
     aanbod
    -0.39
     disfrute
    -0.38
     faveur
    -0.37
    География
    -0.36
     Coordination
    -0.36
     égale
    -0.35
    ünf
    -0.35
     Signalez
    -0.35
    POSITIVE LOGITS
     Roskov
    0.49
    adaptiveStyles
    0.49
    뀐
    0.47
     regained
    0.46
    +:+
    0.45
    principalColumn
    0.45
    LookAnd
    0.43
    Abitanti
    0.43
     regaining
    0.42
     RemoteException
    0.42
    Act Density 0.041%

    No Known Activations