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

    Neuronpedia

    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (k
    -0.07
     iniciar
    -0.06
     jde
    -0.06
     charming
    -0.06
     ib
    -0.06
     captures
    -0.06
     japanese
    -0.06
    Namespace
    -0.06
    терес
    -0.06
     waypoints
    -0.06
    POSITIVE LOGITS
     study
    0.08
     Animator
    0.06
     agar
    0.06
    Study
    0.06
     ToString
    0.06
     vivo
    0.06
     LSM
    0.06
     Study
    0.06
     }↵↵↵↵↵↵
    0.06
     그러나
    0.06
    Act Density 0.018%

    No Known Activations