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
     München
    -0.07
    代理
    -0.07
     version
    -0.07
    recommended
    -0.07
    Controls
    -0.07
     believers
    -0.07
     terme
    -0.07
     Vote
    -0.06
     =&
    -0.06
     banana
    -0.06
    POSITIVE LOGITS
     Buffer
    0.06
     Nem
    0.06
     ech
    0.06
     agar
    0.06
     soma
    0.06
     nêu
    0.06
    alarına
    0.06
    ünü
    0.06
     epith
    0.06
    	ref
    0.06
    Act Density 0.009%

    No Known Activations