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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    htag
    -0.26
    sher
    -0.25
    lington
    -0.24
    æļ´éľ²
    -0.24
     SetUp
    -0.24
    à°³
    -0.23
     cheats
    -0.23
    Exposed
    -0.23
    chester
    -0.23
    icity
    -0.23
    POSITIVE LOGITS
     knot
    0.27
    -based
    0.26
    post
    0.26
    ç»ĵæĻ¶
    0.26
    -ob
    0.24
    -filled
    0.24
    è¯
    0.24
     biology
    0.24
    èĥ¥
    0.24
     constellation
    0.23
    Act Density 0.065%

    No Known Activations