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

    Neuronpedia

    INDEX
    Explanations

    initialize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suspects
    -0.07
     depict
    -0.07
     prudent
    -0.07
     hypoc
    -0.07
     facts
    -0.06
    396
    -0.06
     suspect
    -0.06
    126
    -0.06
     persuade
    -0.06
     top
    -0.06
    POSITIVE LOGITS
    .Initialize
    0.08
    _initialize
    0.08
     initialized
    0.07
    Initialized
    0.07
     initialize
    0.07
     Initialise
    0.07
    OnInit
    0.07
    ]initWith
    0.07
    .pair
    0.07
    annis
    0.07
    Act Density 0.039%

    No Known Activations