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

    Neuronpedia

    INDEX
    Explanations

    effective / efficient suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    すなわち
    1.44
     andra
    1.42
    finders
    1.37
    つまり
    1.31
     czyli
    1.29
     abbreviations
    1.26
    bells
    1.25
    leti
    1.25
    rody
    1.24
     জিনিস
    1.23
    POSITIVE LOGITS
    ️
    2.30
    적인
    1.95
    theless
    1.76
    adays
    1.55
    ︎
    1.53
    ный
    1.52
    ية
    1.48
    િત
    1.47
    ian
    1.44
    ित
    1.44
    Act Density 0.093%

    No Known Activations