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

    Neuronpedia

    INDEX
    Explanations

    sentenced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    βο
    -0.07
     readily
    -0.07
    처
    -0.06
    ्रह
    -0.06
    586
    -0.06
    nings
    -0.06
     biom
    -0.06
    etal
    -0.06
    健
    -0.06
     xin
    -0.06
    POSITIVE LOGITS
     sentenced
    0.10
    igeria
    0.07
      ↵↵
    0.07
    ↵ ↵
    0.07
        ↵↵
    0.06
     renting
    0.06
    sorted
    0.06
     использовани
    0.06
    ']↵↵↵
    0.06
    DidLoad
    0.06
    Act Density 0.001%

    No Known Activations