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

    Neuronpedia

    INDEX
    Explanations

    legal consequences of actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recalc
    0.45
     অ্যাপ্লিকেশন
    0.40
     imprescindible
    0.40
    imens
    0.38
     hierarchical
    0.38
     orthogonal
    0.38
    سترول
    0.38
     diluted
    0.38
     Sail
    0.38
     constrained
    0.37
    POSITIVE LOGITS
     accusations
    0.83
     accused
    0.76
     accusation
    0.73
     wegen
    0.73
     accusing
    0.73
     accuse
    0.72
     vanwege
    0.71
     обви
    0.70
     zbog
    0.70
     acus
    0.67
    Act Density 0.012%

    No Known Activations