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

    Neuronpedia

    INDEX
    Explanations

    ag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brooklyn
    -0.07
    oklyn
    -0.06
     हज
    -0.06
    >M
    -0.06
    Zen
    -0.06
     Slate
    -0.06
     Περ
    -0.06
    udic
    -0.06
    indent
    -0.06
    rama
    -0.06
    POSITIVE LOGITS
    ag
    0.08
     dg
    0.07
     Qed
    0.07
    yps
    0.06
     dağ
    0.06
    .copy
    0.06
     OV
    0.06
    ográf
    0.06
    hay
    0.06
    ้องการ
    0.06
    Act Density 0.002%

    No Known Activations