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

    Neuronpedia

    INDEX
    Explanations

    Tailwind CSS sizes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tional
    2.44
    e
    2.42
    eurs
    2.19
    ection
    2.07
    $).
    2.07
    ت
    1.98
    c
    1.97
    timed
    1.94
    tin
    1.94
    u
    1.92
    POSITIVE LOGITS
     basura
    1.44
    playerId
    1.41
     pâ
    1.39
     média
    1.37
     pouvoir
    1.34
    ę
    1.33
     céu
    1.29
     pede
    1.27
     froid
    1.26
     endroit
    1.26
    Act Density 0.000%

    No Known Activations