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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uges
    -0.06
    graphs
    -0.06
    [val
    -0.06
     extras
    -0.06
     estaba
    -0.06
    둘
    -0.06
    (password
    -0.06
     parametro
    -0.06
    redient
    -0.06
     property
    -0.06
    POSITIVE LOGITS
     •
    0.07
    ANO
    0.07
     Kabul
    0.06
    <Vec
    0.06
    mít
    0.06
     συμπ
    0.06
    but
    0.06
     Alleg
    0.06
     �
    0.06
    英語
    0.06
    Act Density 0.146%

    No Known Activations