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

    Neuronpedia

    INDEX
    Explanations

    will cover or cannot solve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อม
    0.43
    DEBUG
    0.42
    ั
    0.42
     delusion
    0.40
    You
    0.40
     acredito
    0.40
    Ane
    0.39
    ู
    0.39
    с
    0.39
     conceivable
    0.39
    POSITIVE LOGITS
     pihaknya
    0.64
     “…
    0.58
     "...
    0.57
     "..
    0.56
     habían
    0.55
     blah
    0.54
     "'
    0.52
     ইত্যাদি
    0.52
     "`
    0.52
     ήταν
    0.51
    Act Density 0.093%

    No Known Activations