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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pollen
    -0.07
     IQueryable
    -0.07
    �
    -0.07
    шими
    -0.07
    गल
    -0.07
    .Minimum
    -0.07
     Awareness
    -0.06
     cupboard
    -0.06
    株
    -0.06
    .Collections
    -0.06
    POSITIVE LOGITS
    /↵↵↵↵
    0.06
    _tok
    0.06
     Hij
    0.06
    äft
    0.06
     toujours
    0.06
    ॉन
    0.06
     mất
    0.06
     кож
    0.05
     olacağ
    0.05
    ์ได
    0.05
    Act Density 0.000%

    No Known Activations