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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ten
    -0.07
    ывания
    -0.06
    @Inject
    -0.06
    ]],
    -0.06
    .Serve
    -0.06
    Ｓ
    -0.06
     Marin
    -0.06
     Mara
    -0.06
     hran
    -0.06
     πλα
    -0.06
    POSITIVE LOGITS
    จะ
    0.07
    ocities
    0.06
    seat
    0.06
    Method
    0.06
     Cinema
    0.06
    entities
    0.06
     estaba
    0.06
    _PARAMETER
    0.06
     skulle
    0.06
     αυτή
    0.06
    Act Density 0.001%

    No Known Activations