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

    Neuronpedia

    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _empty
    -0.08
    Mind
    -0.07
     postponed
    -0.07
    %%*/
    -0.07
    .flash
    -0.07
     Shine
    -0.06
    ire
    -0.06
     Associ
    -0.06
    .DEFINE
    -0.06
     Summit
    -0.06
    POSITIVE LOGITS
     stál
    0.08
    lbrakk
    0.07
    ง
    0.06
     bert
    0.06
     wäh
    0.06
     znal
    0.06
    Year
    0.06
    ']]['
    0.06
     раза
    0.06
     [.
    0.06
    Act Density 0.144%

    No Known Activations