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

    Neuronpedia

    INDEX
    Explanations

    STAR method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ßt
    -0.08
    quinta
    -0.08
    �
    -0.07
    $\
    -0.07
    Effective
    -0.07
    Inspect
    -0.07
    ?$
    -0.07
    *)"
    -0.07
    Nth
    -0.07
     pa
    -0.07
    POSITIVE LOGITS
    yntax
    0.08
    enn
    0.08
     interactive
    0.08
     argumentative
    0.07
     발표
    0.07
    meden
    0.07
     编
    0.07
    uellement
    0.07
     բ
    0.07
     엔
    0.07
    Act Density 0.002%

    No Known Activations