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

    Neuronpedia

    INDEX
    Explanations

    street address numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snow
    -0.07
     gin
    -0.07
     }]
    -0.07
    Ы
    -0.07
    隊
    -0.07
     prose
    -0.07
    遣
    -0.06
     boca
    -0.06
    obj
    -0.06
    庭
    -0.06
    POSITIVE LOGITS
     olmuş
    0.06
     Originally
    0.06
    たし
    0.06
    áhnout
    0.06
    ida
    0.06
    cycl
    0.06
    .socket
    0.06
     disrupted
    0.06
    xious
    0.06
    Hierarchy
    0.05
    Act Density 0.011%

    No Known Activations