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

    Neuronpedia

    INDEX
    Explanations

    positive aspects of locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .servlet
    -0.08
     NavParams
    -0.07
    -coded
    -0.07
     haircut
    -0.07
     emoji
    -0.07
     AIDS
    -0.07
     Tec
    -0.07
    .idea
    -0.07
     permitting
    -0.07
     LIFE
    -0.07
    POSITIVE LOGITS
    Narr
    0.06
     toe
    0.06
     cruis
    0.06
    _TEM
    0.06
    scratch
    0.05
     лим
    0.05
    resolved
    0.05
     Joined
    0.05
    .bat
    0.05
     елек
    0.05
    Act Density 0.051%

    No Known Activations