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

    Neuronpedia

    INDEX
    Explanations

    constructor parameters like super.key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сло
    0.50
     clar
    0.45
    float
    0.44
    ലീസ്
    0.44
    {
    0.44
     picnic
    0.44
    िकर
    0.43
     patitth
    0.43
     picnics
    0.43
    denom
    0.42
    POSITIVE LOGITS
     ते
    0.54
    æn
    0.48
    apar
    0.47
     account
    0.44
    收
    0.44
    ếu
    0.43
    ana
    0.43
    𝐊
    0.42
     ανά
    0.42
    throp
    0.41
    Act Density 0.000%

    No Known Activations