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

    Neuronpedia

    INDEX
    Explanations

    simplicity and allowing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    対策
    0.45
    Ҥ
    0.44
     հատ
    0.42
     újra
    0.39
     लीजिएगा
    0.37
    NotEmpty
    0.36
    inated
    0.36
    )=(
    0.36
    lobulin
    0.36
     specifically
    0.36
    POSITIVE LOGITS
     passively
    1.09
     simply
    1.02
     quietly
    0.99
     merely
    0.98
     passive
    0.96
     laisser
    0.95
     simplemente
    0.95
     semplicemente
    0.93
     laissent
    0.92
     просто
    0.91
    Act Density 0.044%

    No Known Activations