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

    Neuronpedia

    INDEX
    Explanations

    Code/forum snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.64
     الرخصة
    -0.59
     dieux
    -0.57
     médical
    -0.56
     médicaux
    -0.55
    nasse
    -0.54
     plainte
    -0.54
    mlung
    -0.54
     financières
    -0.54
     Nacionales
    -0.53
    POSITIVE LOGITS
    +#+#
    0.74
    хьтан
    0.60
     <<<<<<<<<<<<<<
    0.52
    UserScript
    0.52
    ophan
    0.51
     pinulongan
    0.48
    theless
    0.48
    leg
    0.47
    tur
    0.47
     Haber
    0.46
    Act Density 0.033%

    No Known Activations