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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hashed
    -0.07
     Metal
    -0.07
     metal
    -0.07
    ůvod
    -0.07
    (signal
    -0.06
     Liên
    -0.06
     laughing
    -0.06
    acco
    -0.06
    frames
    -0.06
     Talking
    -0.06
    POSITIVE LOGITS
     Τα
    0.07
     encontrar
    0.06
     stra
    0.06
    最
    0.06
    くだ
    0.06
    ์ซ
    0.06
     superb
    0.06
    ]!=
    0.06
     Permit
    0.06
    .RemoveAt
    0.06
    Act Density 0.041%

    No Known Activations