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

    Neuronpedia

    INDEX
    Explanations

    iterating over response content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     കൂടി
    0.39
    Nick
    0.37
     Nick
    0.36
    Taj
    0.35
    Hol
    0.34
    Ặ
    0.34
    Tiger
    0.34
    Sig
    0.34
    Del
    0.33
     Tiger
    0.33
    POSITIVE LOGITS
     slu
    0.45
     responsável
    0.42
     stanza
    0.40
     oportunidade
    0.40
     ори
    0.39
     encima
    0.38
     MediaQuery
    0.38
    льку
    0.38
    릅
    0.38
    ϴ
    0.37
    Act Density 0.000%

    No Known Activations