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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LTE
    -0.08
    dB
    -0.08
    Nano
    -0.07
     accord
    -0.07
    也不敢
    -0.07
    ído
    -0.07
    Ipv
    -0.07
    >}</
    -0.07
    UTC
    -0.07
    -0.07
    POSITIVE LOGITS
    	TR
    0.07
    tır
    0.07
     nt
    0.06
     كال
    0.06
     aggravated
    0.06
     Clippers
    0.06
    .sheet
    0.06
     valores
    0.06
    (bb
    0.06
    ascar
    0.06
    Act Density 0.014%

    No Known Activations