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

    Neuronpedia

    INDEX
    Explanations

    Quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tamam
    -0.06
     Far
    -0.06
    (Screen
    -0.06
     соответств
    -0.06
     Umb
    -0.06
    desired
    -0.06
     üz
    -0.06
     đúng
    -0.06
    conds
    -0.06
    props
    -0.06
    POSITIVE LOGITS
     FOOD
    0.07
    inction
    0.07
    <=$
    0.07
    iface
    0.07
    _pemb
    0.07
     Whoever
    0.07
    OB
    0.06
    opped
    0.06
    ажд
    0.06
    _uri
    0.06
    Act Density 0.080%

    No Known Activations