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

    Neuronpedia

    INDEX
    Explanations

    location coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reversals
    0.35
    etli
    0.34
    slan
    0.34
     right
    0.34
    edRight
    0.34
     വല
    0.34
     उल्टा
    0.33
     Routed
    0.33
     pravo
    0.33
     bloss
    0.33
    POSITIVE LOGITS
     twelve
    0.39
     ten
    0.38
    Failure
    0.38
    ten
    0.38
     १२
    0.37
    failure
    0.36
    HOT
    0.36
     هار
    0.35
     failure
    0.35
    Hare
    0.35
    Act Density 0.003%

    No Known Activations