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

    Neuronpedia

    INDEX
    Explanations

    code blocks and execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Const
    0.55
    Fabric
    0.47
    Hyp
    0.47
    Instrumentation
    0.46
    әк
    0.46
    Histogram
    0.45
    ":[
    0.45
    StringBuilder
    0.44
    FileNotFound
    0.44
    Constants
    0.43
    POSITIVE LOGITS
     ouvir
    0.81
     warga
    0.80
     cidad
    0.74
     bicara
    0.73
     cuerpo
    0.72
     vatandaş
    0.71
     oyun
    0.71
     tubuh
    0.70
     turun
    0.70
     dari
    0.69
    Act Density 0.298%

    No Known Activations