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

    Neuronpedia

    INDEX
    Explanations

    missing persons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wd
    -0.07
    	target
    -0.07
    .mouse
    -0.07
     master
    -0.07
    .White
    -0.07
     indie
    -0.07
     guild
    -0.07
     key
    -0.06
    .wallet
    -0.06
     pledged
    -0.06
    POSITIVE LOGITS
    -too
    0.08
     gaan
    0.07
    izar
    0.07
    されました
    0.07
    哝
    0.07
    건설
    0.07
    쳬
    0.07
     abnormalities
    0.07
     Getting
    0.07
    �
    0.07
    Act Density 0.059%

    No Known Activations