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

    Neuronpedia

    INDEX
    Explanations

    AI models and academic programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ponctués
    0.35
    部分的
    0.33
    を経て
    0.33
     alte
    0.33
     wspom
    0.33
    にある
    0.32
     nowego
    0.32
    জনের
    0.32
     industrie
    0.32
     entour
    0.32
    POSITIVE LOGITS
    ®
    0.66
    ®,
    0.63
     itself
    0.62
    ®.
    0.57
    ™
    0.49
    Ⓡ
    0.49
    ian
    0.48
    ™,
    0.45
    its
    0.44
     ®
    0.44
    Act Density 0.220%

    No Known Activations