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

    Neuronpedia

    INDEX
    Explanations

    technical coursework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.47
    }
    0.46
    ни
    0.46
    M
    0.45
     சரியான
    0.44
    Sup
    0.43
    ти
    0.43
    right
    0.42
    {
    0.42
    )
    0.42
    POSITIVE LOGITS
     pavilions
    0.51
    环境
    0.47
     ऑक्साइड
    0.46
     ग्लास
    0.46
    Campe
    0.43
     环境
    0.43
    ሖ
    0.43
    ያን
    0.43
     histidine
    0.43
     inlaid
    0.42
    Act Density 0.000%

    No Known Activations