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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -buy
    -0.07
    .keys
    -0.06
    _Adjust
    -0.06
     yell
    -0.06
    (config
    -0.06
     зав
    -0.06
    .amount
    -0.06
     hone
    -0.06
    (validate
    -0.06
    와
    -0.06
    POSITIVE LOGITS
    퍼
    0.07
     Rid
    0.06
    τωση
    0.06
     bryster
    0.06
     backlog
    0.06
    ρηση
    0.06
    bs
    0.06
     "...
    0.06
    ра�
    0.06
     Interfaces
    0.06
    Act Density 0.073%

    No Known Activations