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

    Neuronpedia

    INDEX
    Explanations

    wraps and sandwiches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utory
    -0.29
    (sym
    -0.27
    #č↵
    -0.25
    éĽ¢
    -0.25
    èªŀè¨Ģ
    -0.24
    celand
    -0.24
    _Format
    -0.24
    á¸ĭ
    -0.24
    Certificates
    -0.23
    alysis
    -0.23
    POSITIVE LOGITS
     i
    0.26
     ï
    0.25
     \
    0.25
    ç²¾
    0.24
    ol
    0.24
    å²·
    0.24
    -inf
    0.24
    ere
    0.24
     fitted
    0.24
     Kashmir
    0.24
    Act Density 0.231%

    No Known Activations