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

    Neuronpedia

    INDEX
    Explanations

    lists or numerical points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oha
    0.51
     заряда
    0.45
    ’
    0.45
     начал
    0.41
     multiplied
    0.40
     Trails
    0.40
    ról
    0.40
     Calculation
    0.40
     Targets
    0.40
    had
    0.40
    POSITIVE LOGITS
     ק
    0.50
     macrom
    0.49
    מי
    0.48
    ність
    0.48
     inconsist
    0.47
    ک
    0.47
    }=$
    0.46
    jonal
    0.46
    י
    0.46
    𝒄
    0.46
    Act Density 0.001%

    No Known Activations