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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusion or addition of information

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

    also followed by an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThemeOverlay
    -0.48
    لاعات
    -0.41
    ddots
    -0.40
    WebRequest
    -0.38
     damen
    -0.38
    AutoScaleMode
    -0.38
     Roskov
    -0.38
    Roh
    -0.36
    esen
    -0.36
    neet
    -0.36
    POSITIVE LOGITS
     also
    0.94
    also
    0.90
     também
    0.89
     también
    0.89
     Also
    0.88
     également
    0.86
     også
    0.85
    Also
    0.83
     juga
    0.82
     myös
    0.81
    Act Density 0.538%

    No Known Activations