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

    Neuronpedia

    INDEX
    Explanations

    specific characteristics and aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᓄ
    0.41
     looser
    0.37
     вновь
    0.36
     swear
    0.36
     voire
    0.36
    汆
    0.36
     fazia
    0.35
    ళ్
    0.34
    SerializeField
    0.34
     hätte
    0.33
    POSITIVE LOGITS
     specifics
    0.78
     basics
    0.75
     Basics
    0.71
     limitations
    0.69
     drawbacks
    0.65
     peculiarities
    0.65
    特点
    0.62
    basics
    0.61
     caveats
    0.61
     terminology
    0.61
    Act Density 0.071%

    No Known Activations