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

    Neuronpedia

    INDEX
    Explanations

    given a task or role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iyati
    0.40
     dispensed
    0.40
     yield
    0.38
     ;
    0.38
     yielding
    0.38
    ISHING
    0.37
    氀
    0.36
    形態
    0.36
     inserted
    0.35
     yielded
    0.35
    POSITIVE LOGITS
     onto
    0.57
     unanimously
    0.46
     to
    0.46
    onto
    0.46
     ufficial
    0.43
     nhiệm
    0.42
     проведение
    0.42
     guardian
    0.41
     probationary
    0.41
     Honorary
    0.40
    Act Density 0.010%

    No Known Activations