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

    Neuronpedia

    INDEX
    Explanations

    say population

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vím
    -0.06
     McKin
    -0.06
     Kre
    -0.06
     Giants
    -0.06
     eid
    -0.06
    edeki
    -0.06
    lacak
    -0.05
     cuatro
    -0.05
    ěti
    -0.05
     swims
    -0.05
    POSITIVE LOGITS
    _refer
    0.06
    ctrl
    0.06
    .dm
    0.06
    鄉
    0.06
     respectfully
    0.06
    defer
    0.06
    .Misc
    0.06
     malfunction
    0.06
     namedtuple
    0.06
    appy
    0.06
    Act Density 0.083%

    No Known Activations