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

    Neuronpedia

    INDEX
    Explanations

    haunted by past mistakes and regret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    0.54
    。”
    0.46
    ܘܢ
    0.46
    physiology
    0.45
     hydrology
    0.44
    ية
    0.44
    ن
    0.44
    初
    0.43
     فه
    0.42
    websocket
    0.42
    POSITIVE LOGITS
     seçenek
    0.45
    czak
    0.45
     situé
    0.44
     Locate
    0.43
    strdup
    0.43
    an
    0.43
     valid
    0.43
    Bold
    0.42
     sudo
    0.42
    টিত
    0.41
    Act Density 0.000%

    No Known Activations