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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gentlemen
    -0.06
    }↵↵↵↵↵
    -0.06
     hype
    -0.06
     如
    -0.06
    "http
    -0.06
    apture
    -0.06
     auch
    -0.06
    actually
    -0.06
     lxml
    -0.06
    點
    -0.06
    POSITIVE LOGITS
     dresser
    0.07
     furn
    0.07
     Crystal
    0.07
     Habitat
    0.06
     strides
    0.06
     avan
    0.06
     SORT
    0.06
     biom
    0.06
    Jan
    0.06
    .showError
    0.06
    Act Density 0.087%

    No Known Activations