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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']=="
    -0.08
    .arch
    -0.07
     valid
    -0.07
    /error
    -0.06
    Transmission
    -0.06
    ?><
    -0.06
     PLAN
    -0.06
     NORMAL
    -0.06
    ınız
    -0.06
    +B
    -0.06
    POSITIVE LOGITS
    ùy
    0.07
    -enh
    0.06
    .Ph
    0.06
    剣
    0.06
    ικοί
    0.06
    ATTERN
    0.06
     expelled
    0.06
    vector
    0.06
     dye
    0.06
    SED
    0.06
    Act Density 0.130%

    No Known Activations