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

    Neuronpedia

    INDEX
    Explanations

    DF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coat
    -0.07
     Lumpur
    -0.07
    )))),
    -0.07
     قاب
    -0.07
     []);↵↵
    -0.07
    diği
    -0.07
     CMP
    -0.07
    acet
    -0.07
    Workspace
    -0.07
     nhằm
    -0.06
    POSITIVE LOGITS
    ลา
    0.06
    lava
    0.06
    assemble
    0.06
    ycles
    0.06
     refer
    0.06
     العالم
    0.06
     roundup
    0.06
    ै?↵
    0.06
    yses
    0.06
    度
    0.06
    Act Density 0.005%

    No Known Activations