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

    Neuronpedia

    INDEX
    Explanations

    ASCII art characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     仮
    0.72
     presumption
    0.72
     Mechanism
    0.70
    サム
    0.68
     mechanism
    0.68
     MODULE
    0.67
     axiomatic
    0.65
     跳
    0.65
    mechanism
    0.65
    疑問
    0.64
    POSITIVE LOGITS
    ovsk
    0.67
    丅
    0.65
     tene
    0.65
     szerint
    0.62
    Level
    0.62
     Flatten
    0.61
    eyn
    0.61
    rients
    0.60
    gtr
    0.60
     nagyobb
    0.60
    Act Density 0.023%

    No Known Activations