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

    Neuronpedia

    INDEX
    Explanations

    dream followed by related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ี
    0.89
    .
    0.89
    ко
    0.88
    ни
    0.88
    dı
    0.86
    druck
    0.86
    ку
    0.81
    ا
    0.80
    ди
    0.79
    джи
    0.78
    POSITIVE LOGITS
    },
    0.85
    jų
    0.84
    ilor
    0.81
    মন্ত্রী
    0.80
    টি
    0.77
    شود
    0.76
     Polonia
    0.76
    ową
    0.76
     neke
    0.76
     informó
    0.75
    Act Density 0.007%

    No Known Activations