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

    Neuronpedia

    INDEX
    Explanations

    dream catchers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    funk
    -0.08
    ергә
    -0.08
    꿈
    -0.08
    να
    -0.08
    。从
    -0.08
     funk
    -0.07
     кі
    -0.07
    볼
    -0.07
     pung
    -0.07
    充
    -0.07
    POSITIVE LOGITS
    Only
    0.08
     declines
    0.07
     changes
    0.07
    yside
    0.07
     Only
    0.07
    Changes
    0.07
    _As
    0.07
     As
    0.07
    As
    0.07
     rääk
    0.07
    Act Density 0.000%

    No Known Activations