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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !")↵↵
    -0.08
     또
    -0.08
    cret
    -0.08
     dés
    -0.08
     pros
    -0.08
    )↵↵
    -0.08
      ↵    ↵
    -0.08
    	r
    -0.08
    ***↵↵
    -0.07
    awk
    -0.07
    POSITIVE LOGITS
    ter
    0.08
    LO
    0.08
    lo
    0.08
    local
    0.08
    ra
    0.08
    ca
    0.07
    	se
    0.07
    nce
    0.07
    per
    0.07
    act
    0.07
    Act Density 0.763%

    No Known Activations