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

    Neuronpedia

    INDEX
    Explanations

    figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overseeing
    -0.08
    .Criteria
    -0.07
     Dodgers
    -0.06
     karena
    -0.06
     peasants
    -0.06
    'nda
    -0.06
    ',['
    -0.06
    Angular
    -0.06
    angi
    -0.06
    .Usuario
    -0.06
    POSITIVE LOGITS
    /target
    0.07
     iCloud
    0.07
     combination
    0.07
    irect
    0.07
    583
    0.06
    wen
    0.06
    -document
    0.06
     thous
    0.06
    delivery
    0.06
    _element
    0.06
    Act Density 0.000%

    No Known Activations