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

    Neuronpedia

    INDEX
    Explanations

    analysis request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laced
    0.50
     GameObject
    0.48
    icosa
    0.48
     harnessed
    0.48
     parasit
    0.47
    ου
    0.47
    ياز
    0.47
    乗
    0.46
    ва
    0.46
     convertir
    0.46
    POSITIVE LOGITS
    Technical
    0.51
    Tian
    0.51
    poetry
    0.48
    Ticks
    0.47
    Feng
    0.47
    cao
    0.47
     veel
    0.46
    Pie
    0.46
    technical
    0.46
    Tiger
    0.46
    Act Density 0.000%

    No Known Activations