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

    Neuronpedia

    INDEX
    Explanations

    Code and text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .obj
    -0.06
    βάλ
    -0.06
    hasClass
    -0.06
     Paypal
    -0.06
     bakeca
    -0.06
     kök
    -0.06
    액
    -0.06
    manage
    -0.06
     돈
    -0.06
    uitive
    -0.06
    POSITIVE LOGITS
    TON
    0.06
    ton
    0.06
     Receipt
    0.06
    dh
    0.06
    Va
    0.06
     Anatomy
    0.06
    ,V
    0.06
     UB
    0.06
    MENT
    0.06
     photoc
    0.06
    Act Density 0.000%

    No Known Activations