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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Certificate
    -0.07
    .parser
    -0.07
    Italic
    -0.07
    孙
    -0.07
     certificate
    -0.07
    fork
    -0.07
    Wood
    -0.07
     Drops
    -0.06
     Workers
    -0.06
     Peace
    -0.06
    POSITIVE LOGITS
     oath
    0.07
     Nietzsche
    0.06
     maxx
    0.06
    Provide
    0.06
    нод
    0.06
    ñ
    0.06
    gy
    0.06
    Coordinates
    0.06
    .lastIndexOf
    0.06
    ธ
    0.06
    Act Density 0.050%

    No Known Activations