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

    Neuronpedia

    INDEX
    Explanations

    large number calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cynical
    -0.08
     malfunction
    -0.08
     Sweet
    -0.07
    ((*
    -0.07
     Courts
    -0.07
    ăt
    -0.07
     Pleasant
    -0.07
     Scrum
    -0.07
    Glad
    -0.07
     Glad
    -0.07
    POSITIVE LOGITS
     enormous
    0.18
     huge
    0.17
     gigantic
    0.15
     monstrous
    0.14
     огромное
    0.14
     огром
    0.14
     trillion
    0.13
     ogrom
    0.13
     enorm
    0.13
     enormously
    0.13
    Act Density 0.079%

    No Known Activations