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

    Neuronpedia

    INDEX
    Explanations

    announce

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caught
    1.15
     chatted
    1.05
     talked
    1.04
     spoke
    1.03
     visited
    0.99
    caught
    0.94
     catch
    0.88
     catching
    0.85
     побы
    0.85
    catch
    0.84
    POSITIVE LOGITS
     announces
    1.73
     announce
    1.72
     Announces
    1.54
     announcing
    1.52
     anuncia
    1.46
     announced
    1.45
    宣布
    1.37
     anunciar
    1.36
     announcement
    1.35
     anunciou
    1.33
    Act Density 0.081%

    No Known Activations