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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     makes
    -0.08
    /pm
    -0.07
     CPUs
    -0.07
     outsider
    -0.07
    .android
    -0.07
    (plane
    -0.07
    _nf
    -0.07
    Files
    -0.06
    中场
    -0.06
     football
    -0.06
    POSITIVE LOGITS
    .learn
    0.07
    躞
    0.07
    DataAdapter
    0.07
    侏
    0.07
     mie
    0.07
    �
    0.07
     washington
    0.06
     Thy
    0.06
     مست
    0.06
    ','');↵
    0.06
    Act Density 0.100%

    No Known Activations