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

    Neuronpedia

    INDEX
    Explanations

    learning and compatibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     igre
    0.55
     elevationMap
    0.53
     extravag
    0.50
     مارس
    0.47
    resTmp
    0.47
    ufieurs
    0.47
     ლ
    0.46
    ❾
    0.46
    ieurs
    0.46
     pdelay
    0.46
    POSITIVE LOGITS
    IN
    0.57
    acca
    0.50
    B
    0.46
    st
    0.46
    та
    0.46
    stance
    0.46
    et
    0.46
    AN
    0.45
     B
    0.45
     The
    0.45
    Act Density 0.028%

    No Known Activations