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

    Neuronpedia

    INDEX
    Explanations

    neural network source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    refer
    -0.08
    cole
    -0.07
    _z
    -0.07
    ochen
    -0.06
    (t
    -0.06
     pickup
    -0.06
    fers
    -0.06
    workspace
    -0.06
    factory
    -0.06
    Coord
    -0.06
    POSITIVE LOGITS
     forState
    0.07
     srov
    0.07
    身
    0.07
    ;!
    0.07
     superheroes
    0.06
    ancements
    0.06
    FromFile
    0.06
     de
    0.06
     Warner
    0.06
     Elegant
    0.06
    Act Density 0.005%

    No Known Activations