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

    Neuronpedia

    INDEX
    Explanations

    virtual box / for real

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exclude
    0.38
    complex
    0.38
    prepared
    0.38
    reverse
    0.37
    ajo
    0.37
    classifier
    0.37
    尽
    0.37
     diseño
    0.37
     pering
    0.37
    persistent
    0.37
    POSITIVE LOGITS
    पीरियंस
    0.42
    คับ
    0.40
     trp
    0.40
    റ്റ്
    0.39
    ဘာ
    0.37
    urang
    0.37
    ImgBoard
    0.37
     次元
    0.37
    คาเด
    0.36
     dbcontext
    0.36
    Act Density 0.009%

    No Known Activations