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

    Neuronpedia

    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     besten
    -0.06
     Hun
    -0.06
     kt
    -0.06
     �
    -0.06
     activation
    -0.06
     et
    -0.06
     sto
    -0.06
     rgb
    -0.06
     garlic
    -0.06
     zost
    -0.06
    POSITIVE LOGITS
     setDescription
    0.06
    ensburg
    0.06
     Tear
    0.06
    0.06
    клад
    0.06
    0.06
    crollView
    0.06
     Baltimore
    0.06
    obuf
    0.06
     преп
    0.06
    Act Density 0.037%

    No Known Activations