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

    Neuronpedia

    INDEX
    Explanations

    STEM fields, interest, education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ления
    0.64
    é
    0.62
    وم
    0.60
    um
    0.59
    UM
    0.59
    ри
    0.57
    ление
    0.55
    بور
    0.55
    cro
    0.54
    し
    0.54
    POSITIVE LOGITS
     STEM
    1.02
     STEAM
    0.77
            
    0.66
    STEM
    0.62
     מה
    0.57
     cứu
    0.57
     στε
    0.57
    )"))
    0.56
    Ջ
    0.56
    ahasan
    0.54
    Act Density 0.001%

    No Known Activations