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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cwd
    -0.07
    .assignment
    -0.06
     mbox
    -0.06
    _RDONLY
    -0.06
    λογή
    -0.06
     Amnesty
    -0.06
    715
    -0.06
    %H
    -0.06
     experimental
    -0.06
    312
    -0.06
    POSITIVE LOGITS
     partie
    0.07
     mism
    0.07
     quam
    0.06
     женщин
    0.06
     dg
    0.06
    ρεια
    0.06
    ija
    0.06
     positions
    0.06
    카지노
    0.06
     bä
    0.06
    Act Density 0.000%

    No Known Activations