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

    Neuronpedia

    INDEX
    Explanations

    Overwritten/deleted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    then
    -0.09
     outskirts
    -0.07
     kvinder
    -0.07
    mdat
    -0.07
     Bonds
    -0.07
     Sanders
    -0.06
    ันท
    -0.06
     presidents
    -0.06
     Delhi
    -0.06
     propaganda
    -0.06
    POSITIVE LOGITS
    cribed
    0.07
    �
    0.06
    ！");↵
    0.06
     amy
    0.06
     debates
    0.06
    WAIT
    0.06
    .TableName
    0.06
    \R
    0.06
    (GET
    0.06
     tempting
    0.06
    Act Density 0.014%

    No Known Activations