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

    Neuronpedia

    INDEX
    Explanations

    Cheaper versus expensive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nora
    -0.07
     adventurous
    -0.07
     Play
    -0.06
     Devin
    -0.06
     parse
    -0.06
    otope
    -0.06
     Berry
    -0.06
     dynamics
    -0.06
    isify
    -0.06
     GetById
    -0.06
    POSITIVE LOGITS
    ------------------------------------------------------------------------------------------------
    0.07
     trolls
    0.06
    conduct
    0.06
    loff
    0.06
     эф
    0.06
     timeStamp
    0.06
     �
    0.06
    莫
    0.06
    冒
    0.06
     vỏ
    0.06
    Act Density 0.130%

    No Known Activations