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

    Neuronpedia

    INDEX
    Explanations

    destruct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acias
    -0.07
     Fey
    -0.07
     sly
    -0.07
     trovare
    -0.07
    (cmd
    -0.06
     mutex
    -0.06
     rumored
    -0.06
     lone
    -0.06
     smear
    -0.06
     smiling
    -0.06
    POSITIVE LOGITS
    創
    0.08
    .Gen
    0.07
     desenv
    0.07
     cornerstone
    0.07
    نية
    0.06
     destructive
    0.06
     Effect
    0.06
    ˘
    0.06
     Influence
    0.06
    出品
    0.06
    Act Density 0.016%

    No Known Activations