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

    Neuronpedia

    INDEX
    Explanations

    commands or suggestions related to maintaining communication and connection

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

    maintain state or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.68
    rungsseite
    -0.65
    ThroughAttribute
    -0.59
    лтемелер
    -0.54
    /**
    -0.51
    UserScript
    -0.51
    -0.50
     ProtoMessage
    -0.49
    UnusedPrivate
    -0.49
     MSR
    -0.49
    POSITIVE LOGITS
    Keep
    1.37
     Keep
    1.34
    keep
    1.02
    KEEP
    0.90
     KEEP
    0.87
     keep
    0.82
    KeepAlive
    0.67
    keeps
    0.66
     keeps
    0.66
     Keeping
    0.62
    Act Density 0.007%

    No Known Activations