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

    Neuronpedia

    INDEX
    Explanations

    finding code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     favoured
    0.40
     crud
    0.37
     favored
    0.36
     favours
    0.36
    AddModel
    0.35
     நேரத்தில்
    0.35
     voila
    0.35
     allgemein
    0.34
     καθ
    0.34
    things
    0.34
    POSITIVE LOGITS
    ंगाई
    0.43
     identificado
    0.38
    ulfate
    0.38
    Buscar
    0.37
     Buscar
    0.37
     شناس
    0.37
     denaro
    0.37
     населення
    0.37
     مج
    0.37
    idual
    0.36
    Act Density 0.000%

    No Known Activations