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

    Neuronpedia

    INDEX
    Explanations

    specific aspect, such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ycin
    0.73
    년을
    0.71
    년
    0.67
     -=
    0.66
    ]
    0.65
     →
    0.65
    )]
    0.65
    emic
    0.63
     ...]
    0.63
    But
    0.63
    POSITIVE LOGITS
     perhaps
    0.97
    或许
    0.85
     hoff
    0.84
     posiblemente
    0.84
    perhaps
    0.83
     hopefully
    0.83
    Hopefully
    0.83
    hopefully
    0.78
     possibly
    0.77
    Perhaps
    0.77
    Act Density 0.031%

    No Known Activations