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

    Neuronpedia

    INDEX
    Explanations

    building ideas or scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Incorrect
    0.40
     soothing
    0.39
    ޮ
    0.38
     sale
    0.37
     paseo
    0.37
    Validator
    0.37
    often
    0.37
    ఠ
    0.36
    akah
    0.36
     dismal
    0.36
    POSITIVE LOGITS
     expiry
    0.46
    網站
    0.40
    عنی
    0.39
    我們
    0.39
    মতে
    0.38
     utilises
    0.38
     bọn
    0.37
     utilised
    0.37
    essayer
    0.37
     عندنا
    0.36
    Act Density 0.002%

    No Known Activations