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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Champions
    -0.09
    rights
    -0.08
     OID
    -0.07
    ampions
    -0.07
     �
    -0.07
     ends
    -0.07
    ара
    -0.06
     Invoke
    -0.06
     Edwards
    -0.06
    Unary
    -0.06
    POSITIVE LOGITS
    .Abstract
    0.07
    .twig
    0.06
     mistress
    0.06
    ScrollPane
    0.06
    0.06
    /Public
    0.06
     drastically
    0.06
    _sy
    0.06
    _initialize
    0.06
    每
    0.06
    Act Density 0.018%

    No Known Activations