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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.73
    )_/¯
    -0.66
     Drapeau
    -0.64
     nakalista
    -0.63
    WebServlet
    -0.63
    RegressionTest
    -0.62
    曖昧さ回避
    -0.60
     يتيمه
    -0.60
    GOTREF
    -0.59
    NameInMap
    -0.59
    POSITIVE LOGITS
     latest
    0.84
    latest
    0.75
     recent
    0.70
    recent
    0.66
     labor
    0.65
    Latest
    0.64
     presidency
    0.64
    labour
    0.63
    Recent
    0.58
     those
    0.58
    Act Density 0.004%

    No Known Activations