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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    علق
    -0.07
    STITUTE
    -0.06
    spinner
    -0.06
    ….
    -0.06
    ead
    -0.06
    ตา
    -0.06
    ()"
    -0.06
    ерату
    -0.06
     THEORY
    -0.06
    erable
    -0.06
    POSITIVE LOGITS
     NHL
    0.07
    elems
    0.07
     establish
    0.06
     Chad
    0.06
     Temporary
    0.06
     preference
    0.06
     massacre
    0.06
     Dame
    0.06
     prop
    0.06
     Undefined
    0.06
    Act Density 0.084%

    No Known Activations