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

    Neuronpedia

    INDEX
    Explanations

    tentative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ))));
    -0.75
    oid
    -0.74
     Transverse
    -0.72
    )));
    -0.70
    일에
    -0.69
     još
    -0.68
    iti
    -0.68
     elecciones
    -0.67
     forcefully
    -0.66
    이드
    -0.66
    POSITIVE LOGITS
    ative
    1.70
    ativeness
    1.70
    atively
    1.48
    ATIVE
    1.24
    itive
    1.16
    tative
    1.09
    poles
    0.93
    ulative
    0.90
    ITIVE
    0.90
    tive
    0.89
    Act Density 0.031%

    No Known Activations