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

    Neuronpedia

    INDEX
    Explanations

    min, adrenaline, controller, January

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इतर
    0.50
     інших
    0.48
     chatted
    0.47
    0.47
     generalizing
    0.46
     кома
    0.45
    ЕД
    0.45
     }{\
    0.45
     tags
    0.45
    숟
    0.45
    POSITIVE LOGITS
    an
    0.49
    in
    0.46
    provides
    0.42
    ate
    0.42
    currentColor
    0.42
    le
    0.41
    í
    0.41
    this
    0.41
    c
    0.41
    Ru
    0.40
    Act Density 0.000%

    No Known Activations