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

    Neuronpedia

    INDEX
    Explanations

    programming documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deserved
    -0.10
     sympat
    -0.09
     rehab
    -0.09
     dermat
    -0.09
     revital
    -0.09
     wow
    -0.09
     brindar
    -0.09
     bienes
    -0.09
     postpartum
    -0.09
     breakthrough
    -0.09
    POSITIVE LOGITS
    指定
    0.10
     Unary
    0.10
     configurable
    0.10
    CPU
    0.10
     optionally
    0.10
    normally
    0.10
    :↵//↵//
    0.09
     selectable
    0.09
     지정
    0.09
    enging
    0.09
    Act Density 0.175%

    No Known Activations