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

    Neuronpedia

    INDEX
    Explanations

    last + time/event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    早速
    0.92
    दारी
    0.86
    ietta
    0.86
    ines
    0.83
    asionally
    0.81
     swells
    0.81
    ит
    0.81
     imply
    0.78
    期間
    0.77
    主义
    0.77
    POSITIVE LOGITS
     bastion
    1.36
     gasp
    1.34
     resorts
    1.33
     resort
    1.32
     hur
    1.26
     vestiges
    1.23
    minute
    1.23
    onbury
    1.15
     ditch
    1.13
     rites
    1.10
    Act Density 0.069%

    No Known Activations