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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or negativity

    oai_token-act-pair · gemini-2.0-flash

    yet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    balleur
    -0.52
     Geiger
    -0.50
     Mifflin
    -0.49
    bolista
    -0.47
    âte
    -0.47
    ffindor
    -0.46
    gwt
    -0.45
    cloudflare
    -0.44
     voyons
    -0.44
     ionizing
    -0.44
    POSITIVE LOGITS
     Normdatei
    0.84
     ivelany
    0.65
     المعيارى
    0.61
    íncia
    0.60
    GraphicsUnit
    0.59
     referenties
    0.58
    AddTagHelper
    0.56
    enumi
    0.56
    __":
    0.54
     another
    0.54
    Act Density 8.339%

    No Known Activations