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

    Neuronpedia

    INDEX
    Explanations

    first person plural pronouns, numbers and indefinite articles

    oai_token-act-pair · gemini-2.0-flash

    Job descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     étoit
    -0.76
    يكب
    -0.72
     صوتيه
    -0.71
    WriteBarrier
    -0.70
    /*
    -0.66
    addCriterion
    -0.66
     المعيارى
    -0.65
     متعلقه
    -0.65
     auroit
    -0.65
    TestingModule
    -0.64
    POSITIVE LOGITS
     heraus
    0.50
     kan
    0.48
    Issue
    0.46
    Geplaatst
    0.46
     sense
    0.45
    UNIT
    0.45
    supp
    0.45
    hdl
    0.45
    ाम
    0.45
     dynamic
    0.44
    Act Density 0.844%

    No Known Activations