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

    Neuronpedia

    INDEX
    Explanations

    ERA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iers
    -0.08
    piler
    -0.07
    ngx
    -0.07
     morb
    -0.06
    classCallCheck
    -0.06
    AYER
    -0.06
    Still
    -0.06
    anning
    -0.06
     electrons
    -0.06
    insn
    -0.06
    POSITIVE LOGITS
    >A
    0.07
     Sak
    0.07
    Await
    0.07
    的部分
    0.07
     Portable
    0.07
     particip
    0.06
    马拉
    0.06
    번
    0.06
     ah
    0.06
     القدس
    0.06
    Act Density 0.001%

    No Known Activations