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

    Neuronpedia

    INDEX
    Explanations

    cooking with fire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ʟ
    -0.08
     Fallout
    -0.07
    Leader
    -0.07
    YP
    -0.07
    𝓇
    -0.07
     ET
    -0.06
    <Player
    -0.06
     AFL
    -0.06
     Election
    -0.06
    حمل
    -0.06
    POSITIVE LOGITS
     @"\
    0.07
     stratég
    0.07
    =rand
    0.06
     coax
    0.06
    +s
    0.06
     ****************
    0.06
     açıl
    0.06
    ')+
    0.06
    渔民
    0.06
    我们也
    0.06
    Act Density 0.011%

    No Known Activations