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

    Neuronpedia

    INDEX
    Explanations

    increases and decreases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plaster
    -0.06
     Zhao
    -0.06
    us
    -0.06
    	Global
    -0.06
    qrt
    -0.06
     трьох
    -0.06
    _Mod
    -0.06
    Allocator
    -0.06
     Rex
    -0.06
     orchest
    -0.06
    POSITIVE LOGITS
     Increases
    0.09
     reductions
    0.08
     increase
    0.08
     increases
    0.07
    CREASE
    0.07
     Increase
    0.07
    phrase
    0.07
     leap
    0.06
    accordion
    0.06
    anut
    0.06
    Act Density 0.049%

    No Known Activations