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

    Neuronpedia

    INDEX
    Explanations

    awesomeness, awkward, awe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plung
    0.42
     volatil
    0.41
     भोग
    0.41
     fever
    0.40
    द्रोह
    0.39
    యోజ
    0.39
     জেড
    0.39
    恹
    0.39
     Fever
    0.38
     Foli
    0.38
    POSITIVE LOGITS
    Aw
    1.08
     Aw
    1.00
     aw
    0.93
    ESOME
    0.83
     inspiring
    0.82
     awkward
    0.82
     AW
    0.82
    awk
    0.81
     awe
    0.80
    inspiring
    0.80
    Act Density 0.007%

    No Known Activations