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

    Neuronpedia

    INDEX
    Explanations

    the ability to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interfacing
    0.41
     experimenting
    0.41
     plugging
    0.40
     hjæl
    0.40
    дца
    0.40
     preparing
    0.39
    appelijke
    0.39
     zd
    0.38
     piloting
    0.37
    போ
    0.37
    POSITIVE LOGITS
     ability
    0.70
     Ability
    0.68
    Ability
    0.66
    abled
    0.59
    ABILITY
    0.50
     способность
    0.48
     能力
    0.48
    能力
    0.47
     Fäh
    0.46
     abil
    0.46
    Act Density 0.002%

    No Known Activations