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

    Neuronpedia

    INDEX
    Explanations

    library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    creator
    -0.07
     fry
    -0.07
    serialization
    -0.07
    Executing
    -0.07
    ,idx
    -0.07
    .File
    -0.06
    abwe
    -0.06
    Material
    -0.06
     MATERIAL
    -0.06
     Vit
    -0.06
    POSITIVE LOGITS
     [@
    0.07
    decay
    0.06
     müşteri
    0.06
     Dad
    0.06
     onChange
    0.06
    years
    0.06
     SM
    0.06
     Sc
    0.06
     "-";↵
    0.05
    å
    0.05
    Act Density 0.002%

    No Known Activations