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

    Neuronpedia

    INDEX
    Explanations

    terms related to processes or actions in a scientific or technical context

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

    followed by mathematical operations or symbols

    np_acts-logits-general · gemini-2.0-flash

    Calculate, collect, denote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.69
     "..\..\..\
    -0.64
    ^(@)
    -0.59
    };*/
    -0.58
    ukone
    -0.58
    حياته
    -0.56
    Wut
    -0.56
    ariConfig
    -0.55
    ]--;
    -0.54
    Santis
    -0.54
    POSITIVE LOGITS
     the
    1.60
    the
    0.79
    The
    0.69
     The
    0.65
    <bos>
    0.58
     THE
    0.57
     aikana
    0.55
     magát
    0.54
     την
    0.53
    の
    0.53
    Act Density 0.343%

    No Known Activations