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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Daddy
    -0.09
    Brains
    -0.08
    inputs
    -0.08
    .inputs
    -0.08
     Customize
    -0.08
    .state
    -0.08
    Customize
    -0.08
    state
    -0.08
    Feder
    -0.08
    fassung
    -0.08
    POSITIVE LOGITS
     таким
    0.08
    /conf
    0.08
     ila
    0.08
     discontinu
    0.07
     Mg
    0.07
     Horton
    0.07
     прит
    0.07
     breached
    0.07
     закреп
    0.07
     подтверд
    0.07
    Act Density 0.001%

    No Known Activations