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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     {};↵
    -0.06
     clip
    -0.06
    Trait
    -0.05
     pests
    -0.05
     RV
    -0.05
     raped
    -0.05
     DISCLAIM
    -0.05
     dumps
    -0.05
    vasive
    -0.05
     tam
    -0.05
    POSITIVE LOGITS
     Shir
    0.08
     poč
    0.07
     Bangkok
    0.07
    	BufferedReader
    0.07
    iday
    0.07
    ,S
    0.07
    Af
    0.06
    _sock
    0.06
     EITHER
    0.06
    excerpt
    0.06
    Act Density 0.347%

    No Known Activations