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

    Neuronpedia

    INDEX
    Explanations

    location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FSIZE
    -0.07
    bubble
    -0.06
     Frag
    -0.06
    Heat
    -0.06
    ład
    -0.06
     cif
    -0.06
    hay
    -0.06
     AR
    -0.06
     اتحاد
    -0.06
    MO
    -0.06
    POSITIVE LOGITS
    .pages
    0.07
    lač
    0.07
     Squ
    0.06
     revert
    0.06
    用户
    0.06
    }},
    0.06
     영향
    0.06
     двор
    0.06
     Exact
    0.06
    拼
    0.06
    Act Density 0.046%

    No Known Activations