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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Strat
    -0.07
     �
    -0.06
     deer
    -0.06
     validators
    -0.06
     ring
    -0.06
    cors
    -0.06
     tre
    -0.06
    ami
    -0.06
     gebruik
    -0.06
    mour
    -0.06
    POSITIVE LOGITS
    大阪
    0.07
    zza
    0.07
     اذ
    0.07
     αλλά
    0.06
    ertoire
    0.06
    назнач
    0.06
     thập
    0.06
    _FILES
    0.06
    発表
    0.06
    rossover
    0.06
    Act Density 0.118%

    No Known Activations