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

    Neuronpedia

    INDEX
    Explanations

    can cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    V
    0.50
    INV
    0.44
    Ph
    0.43
    Be
    0.40
    We
    0.39
    W
    0.39
    Sim
    0.39
     Spreadsheet
    0.39
    Un
    0.38
     Desktop
    0.38
    POSITIVE LOGITS
     walkable
    0.46
    𒊏
    0.45
     coronae
    0.44
    阿里巴巴
    0.43
     kudos
    0.43
    terminus
    0.42
     KPMG
    0.41
     Kylie
    0.41
     mastectomy
    0.40
     pedicure
    0.40
    Act Density 0.000%

    No Known Activations