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

    Neuronpedia

    INDEX
    Explanations

    often with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amoureux
    0.51
    栆
    0.49
    ⽤
    0.49
     Ashe
    0.47
    Fert
    0.46
    汙
    0.46
     保存
    0.46
    Swatch
    0.46
    Pourquoi
    0.45
    DeleteItem
    0.45
    POSITIVE LOGITS
     on
    0.50
    inescence
    0.46
     raided
    0.45
    ą
    0.44
     can
    0.43
    š
    0.43
    нього
    0.43
     recid
    0.41
     complimented
    0.41
     is
    0.41
    Act Density 0.008%

    No Known Activations