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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prosecute
    -0.06
     stunt
    -0.06
    ,</
    -0.06
    (Msg
    -0.05
     متح
    -0.05
     कह
    -0.05
     ايران
    -0.05
    也不
    -0.05
    甚
    -0.05
     �
    -0.05
    POSITIVE LOGITS
    call
    0.08
     TensorFlow
    0.07
    #[
    0.07
     FEATURE
    0.07
     '''
    0.07
    \F
    0.07
    Phys
    0.07
    0.06
     Compet
    0.06
    installer
    0.06
    Act Density 0.084%

    No Known Activations