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

    Neuronpedia

    INDEX
    Explanations

    word endings forming adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initiation
    0.32
     gazebo
    0.31
     laissant
    0.31
     створення
    0.30
     잘
    0.30
     tedious
    0.30
     الرا
    0.30
    вання
    0.30
     간단
    0.30
     스스로
    0.30
    POSITIVE LOGITS
    ized
    0.38
    itelisted
    0.37
    ed
    0.36
    ளது
    0.34
    edly
    0.34
    eritud
    0.33
    된
    0.33
    9
    0.32
    _
    0.32
    ised
    0.32
    Act Density 0.109%

    No Known Activations