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

    Neuronpedia

    INDEX
    Explanations

    Pix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Walker
    -0.08
    <System
    -0.08
     Demon
    -0.08
     הנ
    -0.07
     Activ
    -0.07
     Bearing
    -0.07
    Exercise
    -0.07
     Procedure
    -0.07
     Mund
    -0.07
     shoes
    -0.07
    POSITIVE LOGITS
     assistir
    0.07
     -->↵
    0.07
    ۇ
    0.06
    万亿元
    0.06
    溇
    0.06
    .HttpStatus
    0.06
    ѿ
    0.06
    -but
    0.06
    晒
    0.06
    急需
    0.06
    Act Density 0.010%

    No Known Activations