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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    safe
    -0.07
    ,
↵
    -0.07
    esar
    -0.07
    від
    -0.06
    ,g
    -0.06
    .jupiter
    -0.06
     Dud
    -0.06
    .sz
    -0.06
     ",
    -0.06
     conte
    -0.06
    POSITIVE LOGITS
    .Print
    0.07
     came
    0.06
     mechanism
    0.06
    ิยม
    0.06
     Civil
    0.06
    %!
    0.06
    _itr
    0.06
     Interest
    0.06
    akedirs
    0.06
    國
    0.06
    Act Density 0.019%

    No Known Activations