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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    encoded
    -0.07
    OrFail
    -0.07
    _REGION
    -0.07
    =node
    -0.07
    สด
    -0.06
    ъек
    -0.06
    xAF
    -0.06
     biome
    -0.06
     hạ
    -0.06
    ㅋㅋ
    -0.06
    POSITIVE LOGITS
    ★★
    0.07
     Never
    0.06
     terk
    0.06
     PSI
    0.06
    one
    0.06
     McGu
    0.06
     tutti
    0.06
     WANT
    0.06
    _INVALID
    0.06
    MetaData
    0.06
    Act Density 0.044%

    No Known Activations