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

    Neuronpedia

    INDEX
    Explanations

    Java documentation references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bounding
    -0.06
    Christian
    -0.06
    veillance
    -0.06
     entrepreneur
    -0.06
    steller
    -0.06
    Ear
    -0.06
    jan
    -0.06
     thirteen
    -0.06
     extortion
    -0.06
    arian
    -0.06
    POSITIVE LOGITS
    ‌تر
    0.07
     Durant
    0.06
    _TAG
    0.06
     crushed
    0.06
    ــــــــ
    0.06
    snake
    0.06
     Rogue
    0.06
    .sun
    0.06
     tük
    0.06
    _Pl
    0.06
    Act Density 0.001%

    No Known Activations