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

    Neuronpedia

    INDEX
    Explanations

    cool temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.70
     z
    0.65
     Jürgen
    0.63
     TAU
    0.62
     Ivan
    0.61
     Tau
    0.60
     з
    0.60
    gul
    0.58
     DVD
    0.58
     eternal
    0.57
    POSITIVE LOGITS
     সমগ্র
    0.63
    긔
    0.63
    fice
    0.60
     pendapatan
    0.60
     poitrine
    0.59
    xlabel
    0.58
     మారింది
    0.57
     होतं
    0.57
     jährlich
    0.56
     familles
    0.56
    Act Density 0.001%

    No Known Activations