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

    Neuronpedia

    INDEX
    Explanations

    Initials/Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cookies
    -0.06
     Guardians
    -0.06
    ìn
    -0.06
    gratis
    -0.06
     odpově
    -0.06
    rej
    -0.06
     kuruluş
    -0.06
    Half
    -0.06
    _scene
    -0.06
     Christine
    -0.06
    POSITIVE LOGITS
    .Nodes
    0.07
     Spiel
    0.07
     triển
    0.07
    (ui
    0.07
     neglected
    0.07
    .Ed
    0.06
     pickle
    0.06
     �
    0.06
    .patch
    0.06
    lernen
    0.06
    Act Density 0.098%

    No Known Activations