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

    Neuronpedia

    INDEX
    Explanations

    around or within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleinement
    0.55
     isang
    0.54
     suatu
    0.51
     nouveaux
    0.49
     अपना
    0.48
     davantage
    0.48
    મના
    0.48
     sebuah
    0.47
     ihrer
    0.47
     grandes
    0.46
    POSITIVE LOGITS
    statement
    0.61
    นี้
    0.57
     statement
    0.52
    で
    0.50
    texture
    0.50
    这个
    0.50
    This
    0.49
    Original
    0.49
    tone
    0.48
    These
    0.48
    Act Density 0.001%

    No Known Activations