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

    Neuronpedia

    INDEX
    Explanations

    names and references related to scientific authors or contributors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Starobinsky's models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sposa
    -0.51
     nocturno
    -0.46
     jurk
    -0.45
     adik
    -0.44
     leyendas
    -0.42
     ejecutivo
    -0.41
    elett
    -0.41
     putra
    -0.40
     cadeira
    -0.40
     Könige
    -0.39
    POSITIVE LOGITS
    Tikang
    0.72
     nakalista
    0.68
    stdc
    0.57
     betweenstory
    0.56
    ✨:
    0.54
     ब्रेकडाउन
    0.54
    FunctionFlags
    0.52
    TestBed
    0.50
     kasarigan
    0.49
    msgTypes
    0.49
    Act Density 0.067%

    No Known Activations