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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emin
    -0.07
    enu
    -0.07
    169
    -0.07
    ково
    -0.07
     cyc
    -0.06
    perms
    -0.06
    inventory
    -0.06
     Samoa
    -0.06
     bans
    -0.06
     RANGE
    -0.06
    POSITIVE LOGITS
    >;↵
    0.07
    .ibatis
    0.07
    .Sprintf
    0.06
    \Input
    0.06
    (木
    0.06
    _actions
    0.06
    -cert
    0.06
    면서
    0.06
    _)
↵
    0.06
    "/>↵
    0.06
    Act Density 0.010%

    No Known Activations