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

    Neuronpedia

    INDEX
    Explanations

    ui

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lamb
    -0.07
     rn
    -0.07
    .activation
    -0.06
     negotiating
    -0.06
     >/
    -0.06
    ].↵
    -0.06
    #================================================================
    -0.06
    Reply
    -0.06
    andbox
    -0.06
     magnificent
    -0.06
    POSITIVE LOGITS
    arges
    0.07
    (remove
    0.06
    (Color
    0.06
    yonel
    0.06
    ilim
    0.06
     energia
    0.06
     آور
    0.06
    INFRINGEMENT
    0.06
     vé
    0.06
    ısıt
    0.06
    Act Density 0.002%

    No Known Activations