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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("~/
    -0.07
    radio
    -0.07
     север
    -0.07
     tac
    -0.07
    ertino
    -0.06
    .rating
    -0.06
     Anti
    -0.06
     freeway
    -0.06
     Fore
    -0.06
     商
    -0.06
    POSITIVE LOGITS
    _tls
    0.07
     batching
    0.06
     Nike
    0.06
     Harmony
    0.06
     Valor
    0.06
     Gaza
    0.06
    ющая
    0.06
     Newton
    0.06
    enis
    0.06
    克斯
    0.06
    Act Density 0.000%

    No Known Activations