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

    Neuronpedia

    INDEX
    Explanations

    recipes and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mall
    -0.07
     Flying
    -0.07
    Living
    -0.06
     uneasy
    -0.06
    StateManager
    -0.06
     survived
    -0.06
     haul
    -0.06
     lassen
    -0.06
    elled
    -0.06
     Thus
    -0.06
    POSITIVE LOGITS
     lign
    0.07
    [ii
    0.06
     rdf
    0.06
     식
    0.06
     mut
    0.06
    (argument
    0.06
    (period
    0.06
    학년도
    0.06
     мере
    0.06
    yms
    0.06
    Act Density 0.000%

    No Known Activations