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

    Neuronpedia

    INDEX
    Explanations

    tonsillitis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contradictions
    0.67
     egli
    0.65
    אס
    0.63
    ۰
    0.63
     novelists
    0.62
     toxin
    0.58
     revolt
    0.57
     divine
    0.57
    களில்
    0.56
     anxieties
    0.55
    POSITIVE LOGITS
    𝙉
    0.64
    ↵↵
    0.63
    P
    0.61
    Tool
    0.58
    يف
    0.58
    N
    0.58
    B
    0.57
    W
    0.57
    ícula
    0.56
     Tons
    0.55
    Act Density 0.001%

    No Known Activations