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

    Neuronpedia

    INDEX
    Explanations

    ular suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transformers
    -0.07
     truths
    -0.06
     beyond
    -0.06
    提交
    -0.06
    imetype
    -0.06
    fleet
    -0.06
    anian
    -0.06
    остат
    -0.06
     relations
    -0.06
     Estates
    -0.06
    POSITIVE LOGITS
     Vers
    0.07
    Grad
    0.07
     Footer
    0.07
    ='".$_
    0.07
     Guerr
    0.07
    _Bool
    0.06
     newRow
    0.06
     nodded
    0.06
     Under
    0.06
    NBC
    0.06
    Act Density 0.001%

    No Known Activations