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

    Neuronpedia

    INDEX
    Explanations

    patterns in numerical or coded data, likely indicating different status or operational states

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

    protocol abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iſen
    -0.94
    ſchaft
    -0.81
    IsMutable
    -0.80
     ſche
    -0.80
     OMITBAD
    -0.78
     beſte
    -0.77
    tagext
    -0.76
    ロウィン
    -0.74
    ſelf
    -0.74
     zwiſchen
    -0.74
    POSITIVE LOGITS
    ://
    0.29
    Whether
    0.27
    ]*(
    0.25
     Gottes
    0.25
     Whether
    0.24
    AB
    0.24
    A
    0.24
     brasileño
    0.24
    TryGetValue
    0.24
    ])/
    0.24
    Act Density 0.086%

    No Known Activations