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

    Neuronpedia

    INDEX
    Explanations

    om

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    診
    -0.06
    стан
    -0.06
     modal
    -0.06
    Drug
    -0.06
     Tüm
    -0.06
     marked
    -0.06
    ("'"
    -0.06
    contacts
    -0.06
     Spirit
    -0.06
     об
    -0.05
    POSITIVE LOGITS
     desires
    0.07
     approximation
    0.07
    annabin
    0.06
     iterations
    0.06
    renom
    0.06
    cbc
    0.06
    	pw
    0.06
    etSocketAddress
    0.06
    arring
    0.06
    istributed
    0.06
    Act Density 0.006%

    No Known Activations