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

    Neuronpedia

    INDEX
    Explanations

    ages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    offsetof
    -0.07
     stellen
    -0.07
    _bag
    -0.06
     descendants
    -0.06
     roaming
    -0.06
    ffff
    -0.06
     voter
    -0.06
     namedtuple
    -0.06
     URLRequest
    -0.06
    ...)↵↵
    -0.06
    POSITIVE LOGITS
    .cc
    0.07
    �
    0.07
    ży
    0.07
    λία
    0.07
    �
    0.07
    [element
    0.06
    ATION
    0.06
    uous
    0.06
     benches
    0.06
    *g
    0.06
    Act Density 0.005%

    No Known Activations