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

    Neuronpedia

    INDEX
    Explanations

    mechanics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     রাতের
    0.48
    larda
    0.42
    মাধ্যমে
    0.41
    тел
    0.41
     ljubav
    0.41
     marketplaces
    0.40
     marketplace
    0.40
    үр
    0.40
    常见的
    0.40
    身边
    0.39
    POSITIVE LOGITS
    Research
    0.45
     Antennes
    0.43
    Pl
    0.42
    Gib
    0.42
     Research
    0.40
    Jo
    0.38
     Forschungs
    0.38
     Suk
    0.36
    (+
    0.36
     Synopsis
    0.36
    Act Density 0.001%

    No Known Activations