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

    Neuronpedia

    INDEX
    Explanations

    paralle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SHOT
    -0.09
     unimaginable
    -0.08
    汗
    -0.08
     shaved
    -0.08
     سه
    -0.08
     kashe
    -0.08
     unfamiliar
    -0.08
     gén
    -0.08
     mara
    -0.08
     بز
    -0.08
    POSITIVE LOGITS
     stipulated
    0.08
     homolog
    0.08
     properties
    0.08
     input
    0.07
    原则
    0.07
     magnets
    0.07
     formed
    0.07
     accreditation
    0.07
     stiffness
    0.07
    Trib
    0.07
    Act Density 0.005%

    No Known Activations