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

    Neuronpedia

    INDEX
    Explanations

    Code/script fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DOUBLE
    -0.06
     لكن
    -0.06
     Curt
    -0.06
    团
    -0.06
    _write
    -0.06
    альные
    -0.06
    .sync
    -0.06
    ather
    -0.06
    photo
    -0.06
    etect
    -0.06
    POSITIVE LOGITS
    	suite
    0.08
    ขณะท
    0.07
     Reign
    0.07
    826
    0.07
    egasus
    0.07
     Laws
    0.06
     Erica
    0.06
     Fridays
    0.06
    _life
    0.06
     Messaging
    0.06
    Act Density 0.000%

    No Known Activations