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

    Neuronpedia

    INDEX
    Explanations

    ready-made

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Morgen
    -0.07
    xing
    -0.07
     weird
    -0.07
    ]:
↵
    -0.07
    Occurs
    -0.07
    -0.07
     bemerk
    -0.07
     Abend
    -0.07
     Brah
    -0.07
     총
    -0.07
    POSITIVE LOGITS
    existing
    0.13
     turnkey
    0.12
    -existing
    0.12
     готов
    0.11
     existente
    0.11
     predefined
    0.10
    (existing
    0.10
    _existing
    0.10
     existentes
    0.10
     Existing
    0.10
    Act Density 0.021%
    No Known Activations