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
    Aud
    -0.06
     Empty
    -0.06
     revolutions
    -0.06
     Lemon
    -0.06
     Beng
    -0.06
     Thou
    -0.06
    rev
    -0.06
     Worcester
    -0.06
     PPP
    -0.06
    SECOND
    -0.06
    POSITIVE LOGITS
     capture
    0.20
     captured
    0.15
     capturing
    0.14
     Capture
    0.10
    capture
    0.10
    apture
    0.07
    aptured
    0.07
    Capture
    0.07
    icits
    0.07
    hapus
    0.07
    Act Density 0.009%

    No Known Activations