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

    Neuronpedia

    INDEX
    Explanations

    look for or at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ferrugineux
    0.27
    com
    0.26
     डायरे
    0.26
     друз
    0.25
    proxy
    0.25
    ürnberg
    0.25
    0.25
    org
    0.25
    漪
    0.25
    ୯
    0.25
    POSITIVE LOGITS
     forward
    0.38
    Look
    0.33
     👀
    0.32
     look
    0.32
     Look
    0.31
     inward
    0.31
     inwards
    0.31
     at
    0.30
     closely
    0.29
     up
    0.29
    Act Density 0.027%

    No Known Activations