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

    Neuronpedia

    INDEX
    Explanations

    standalone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     процес
    0.75
     convenio
    0.73
     অনুরূপ
    0.72
    cedure
    0.71
     паралле
    0.71
    ชั่น
    0.70
     передба
    0.68
    强势
    0.68
    交代
    0.67
     подчи
    0.67
    POSITIVE LOGITS
     alone
    1.48
     Alone
    1.36
    Alone
    1.26
    alone
    1.25
     Used
    1.24
     standalone
    1.23
     used
    1.21
    Used
    1.14
     naked
    1.14
    Standalone
    1.05
    Act Density 0.651%

    No Known Activations