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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    em
    -0.07
     chicken
    -0.07
    stellung
    -0.07
    资料
    -0.06
    .evaluate
    -0.06
    自动
    -0.06
    AN
    -0.06
    âm
    -0.06
    ur
    -0.06
    aid
    -0.06
    POSITIVE LOGITS
    imated
    0.07
    peats
    0.07
     inkl
    0.07
     명
    0.06
     VOID
    0.06
    >";↵
    0.06
                          ↵
    0.06
     denomination
    0.06
     exploded
    0.06
    *)↵
    0.06
    Act Density 0.194%

    No Known Activations