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

    Neuronpedia

    INDEX
    Explanations

    code elements for web or UI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সাড়া
    0.70
     schme
    0.69
     उबाल
    0.69
    glise
    0.68
    rizioni
    0.67
     Noodles
    0.67
     açúcar
    0.67
     algebra
    0.67
    ódio
    0.66
    裟
    0.66
    POSITIVE LOGITS
    <0xB0>
    0.76
    قت
    0.72
     quadruple
    0.70
    >):
    0.70
    ⑭
    0.68
    cone
    0.67
     keempat
    0.66
    <unused770>
    0.66
    pto
    0.65
     ATI
    0.65
    Act Density 0.008%

    No Known Activations