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

    Neuronpedia

    INDEX
    Explanations

    income figures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nnen
    -0.06
     Scholars
    -0.06
     firefighter
    -0.06
    nor
    -0.06
     Rare
    -0.06
    imus
    -0.06
     вар
    -0.06
    	DBG
    -0.06
     Haus
    -0.06
    omed
    -0.06
    POSITIVE LOGITS
    ้↵
    0.07
    届
    0.07
     perl
    0.07
     elevation
    0.07
    BY
    0.06
     trước
    0.06
     terr
    0.06
    _cap
    0.06
    ै?↵
    0.06
    ानत
    0.06
    Act Density 0.001%

    No Known Activations