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

    Neuronpedia

    INDEX
    Explanations

    interstate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     observers
    -0.07
    VERBOSE
    -0.06
     coloured
    -0.06
     steroid
    -0.06
    .Mesh
    -0.06
    -pass
    -0.06
     fabricated
    -0.06
    Elapsed
    -0.06
     Frankfurt
    -0.06
     güven
    -0.06
    POSITIVE LOGITS
    .twig
    0.07
    ратить
    0.07
     gateway
    0.07
     ;
↵
    0.07
    اوي
    0.07
    .swift
    0.07
    узы
    0.07
     appart
    0.06
    èles
    0.06
    _scaling
    0.06
    Act Density 0.002%

    No Known Activations