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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wares
    -0.07
    nte
    -0.07
    Hyper
    -0.07
    #================================================================
    -0.06
    -mini
    -0.06
     mojo
    -0.06
     Sağ
    -0.06
    (CONT
    -0.06
    ейн
    -0.06
    誤
    -0.06
    POSITIVE LOGITS
     "^
    0.12
    .[
    0.07
    ("^
    0.06
     rng
    0.06
     ^
    0.06
    TRACE
    0.06
     í
    0.06
     fellow
    0.06
     ↑
    0.06
    )^
    0.06
    Act Density 0.001%

    No Known Activations