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

    Neuronpedia

    INDEX
    Explanations

    contextual grammatical elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vanje
    0.45
     Gosudarstvennyj
    0.43
    目标的
    0.43
    ngo
    0.42
     અ
    0.42
    abend
    0.42
     zbog
    0.41
    ින්
    0.41
     minimize
    0.39
    াকর
    0.39
    POSITIVE LOGITS
    raped
    0.41
    เหล่านี้
    0.40
    क्ष
    0.40
    امات
    0.38
    لاحظ
    0.37
    ly
    0.37
    ashes
    0.37
    ve
    0.36
    izzes
    0.36
    configurations
    0.36
    Act Density 0.000%

    No Known Activations