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

    Neuronpedia

    INDEX
    Explanations

    cross-platform, interspecies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etheless
    0.68
    ecimento
    0.63
    メータ
    0.63
    ре
    0.62
    ator
    0.58
    った
    0.58
     নেয়
    0.57
    imeter
    0.57
    のみ
    0.57
    з
    0.57
    POSITIVE LOGITS
     lintas
    0.82
     cross
    0.74
    s
    0.66
    0.63
    CROSS
    0.62
    čiti
    0.62
    The
    0.60
     Cross
    0.60
    Cross
    0.60
     CROSS
    0.60
    Act Density 0.028%

    No Known Activations