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

    Neuronpedia

    INDEX
    Explanations

    week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .amazon
    -0.24
    ether
    -0.24
    BIN
    -0.24
    åĬłå¿«
    -0.24
     while
    -0.23
     preserve
    -0.23
    ÑĤоÑĢ
    -0.23
    antan
    -0.23
    _BINDING
    -0.22
    æĬļ
    -0.22
    POSITIVE LOGITS
    ioni
    0.31
     займ
    0.28
    alon
    0.28
    edException
    0.26
    onas
    0.25
    ä¸įå°ij
    0.25
     shaving
    0.25
    imson
    0.24
    åĬĥ
    0.24
    woff
    0.24
    Act Density 0.011%

    No Known Activations