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

    Neuronpedia

    INDEX
    Explanations

    idiomatic phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оптими
    0.49
    圤
    0.46
    乐观
    0.44
     км
    0.44
    ья
    0.42
     רק
    0.42
     макси
    0.41
    दंड
    0.41
     ঐক্য
    0.40
    км
    0.40
    POSITIVE LOGITS
    Ctrl
    0.41
     spô
    0.40
     sanitizer
    0.39
    rcParams
    0.39
    hadas
    0.39
     Job
    0.39
    detached
    0.38
     skincare
    0.38
     Ctrl
    0.38
     xwe
    0.37
    Act Density 0.007%

    No Known Activations