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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mechanical processes and configurations

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

    vertical line intersected at right angles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.84
    adaptiveStyles
    -0.83
     Meksiku
    -0.82
     betweenstory
    -0.82
    GEBURTSDATUM
    -0.79
     resourceCulture
    -0.79
     للاسماء
    -0.77
    UserScript
    -0.77
    RegressionTest
    -0.77
     AssemblyCulture
    -0.75
    POSITIVE LOGITS
     ulang
    0.34
     turns
    0.32
     pestaña
    0.31
     st
    0.30
     par
    0.30
    ][
    0.29
    st
    0.29
     un
    0.29
     to
    0.28
     gap
    0.28
    Act Density 0.063%

    No Known Activations