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

    Neuronpedia

    INDEX
    Explanations

    leading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monitors
    -0.26
    SAFE
    -0.26
     harb
    -0.25
    soon
    -0.25
    Monitor
    -0.25
     Monitor
    -0.24
     himself
    -0.24
    ä¸ĩåħ¬éĩĮ
    -0.23
     Prem
    -0.23
    -options
    -0.23
    POSITIVE LOGITS
    ering
    0.31
    åĹŁ
    0.28
    åı£
    0.28
    itudes
    0.27
    ifies
    0.25
    è¯įæĿ¡
    0.25
    æĮ¤
    0.25
     Sk
    0.24
    æ¡ij
    0.24
    eria
    0.24
    Act Density 0.004%

    No Known Activations