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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diving
    -0.08
    worked
    -0.07
    desk
    -0.07
    Coding
    -0.07
    ]],
    -0.07
     свою
    -0.07
     игров
    -0.07
    ~,
    -0.07
     Jenn
    -0.07
    痒
    -0.06
    POSITIVE LOGITS
     neces
    0.06
    벚
    0.06
     saç
    0.06
    .Reflection
    0.06
     Apostle
    0.06
    _limit
    0.06
     univers
    0.06
    Gl
    0.06
     Bre
    0.06
     disable
    0.06
    Act Density 0.028%

    No Known Activations