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

    Neuronpedia

    INDEX
    Explanations

    capture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     successors
    -0.07
     seas
    -0.07
     rad
    -0.07
     Weg
    -0.07
     road
    -0.07
    resents
    -0.06
    wd
    -0.06
     ekonom
    -0.06
     om
    -0.06
     Roads
    -0.06
    POSITIVE LOGITS
    Capture
    0.09
    capture
    0.09
     capture
    0.08
     Capture
    0.08
    apture
    0.07
    hare
    0.07
     руч
    0.07
    +".
    0.07
     Gabri
    0.06
     vog
    0.06
    Act Density 0.006%

    No Known Activations