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

    Neuronpedia

    INDEX
    Explanations

    debuted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Route
    -0.07
    营
    -0.07
     catal
    -0.07
     Jain
    -0.07
     dinheiro
    -0.06
     İnsan
    -0.06
     justice
    -0.06
    .cloud
    -0.06
    Iraq
    -0.06
     Müller
    -0.06
    POSITIVE LOGITS
     debuted
    0.11
     debut
    0.10
     premiered
    0.09
    ographed
    0.07
    "default
    0.07
    hey
    0.07
     ”
    0.07
    actly
    0.06
     그러나
    0.06
    startup
    0.06
    Act Density 0.008%

    No Known Activations