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

    Neuronpedia

    INDEX
    Explanations

    command line installations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     München
    0.44
     CentOS
    0.43
     കരു
    0.39
     Declar
    0.39
    ครื่อง
    0.38
     ordinateur
    0.38
    equival
    0.38
     Notepad
    0.38
    PropTypes
    0.37
    MacOS
    0.37
    POSITIVE LOGITS
     github
    0.46
    蟹
    0.43
    vline
    0.43
     fixation
    0.42
    github
    0.41
     nw
    0.41
     heel
    0.39
     تازہ
    0.38
    িন
    0.38
    ң
    0.38
    Act Density 0.259%

    No Known Activations