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

    Neuronpedia

    INDEX
    Explanations

    what does know architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FFIC
    0.39
    мно
    0.37
     pronto
    0.37
    ാവ്
    0.36
     потре
    0.36
     Wyoming
    0.36
    动力
    0.36
    ките
    0.36
    庞
    0.36
    怡
    0.36
    POSITIVE LOGITS
    絘
    0.42
    Ꮔ
    0.41
    Beach
    0.40
    Potential
    0.40
     соль
    0.40
    novation
    0.39
    Dom
    0.39
    Weight
    0.39
     सामु
    0.38
    Trop
    0.38
    Act Density 0.000%

    No Known Activations