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

    Neuronpedia

    INDEX
    Explanations

    Python code, partial function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sine
    -0.08
     Hot
    -0.07
     descendants
    -0.06
    HostException
    -0.06
     sto
    -0.06
     workstation
    -0.06
     Ig
    -0.06
     Rank
    -0.06
     Hok
    -0.06
    Little
    -0.06
    POSITIVE LOGITS
    BMW
    0.07
    jian
    0.07
    acl
    0.07
    чис
    0.07
     totalPrice
    0.07
    ¶¶
    0.06
    _MODAL
    0.06
     밤
    0.06
    #+#+
    0.06
    (codec
    0.06
    Act Density 0.001%

    No Known Activations